Regina Barzilay: Deep Learning for Cancer Diagnosis and Treatment

Regina Barzilay is a professor at MIT and a world-class researcher in natural language processing and applications of deep learning to chemistry and oncology, or the use of deep learning for early diagnosis, prevention and treatment of cancer. She has also been recognized for her teaching of several successful AI-related courses at MIT, including the popular Introduction to Machine Learning course. This conversation is part of the Artificial Intelligence podcast. If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter https://twitter.com/lexfridman, LinkedIn https://www.linkedin.com/in/lexfridman/, Facebook https://www.facebook.com/lexfridman, Medium https://medium.com/@lexfridman, or YouTube https://www.youtube.com/lexfridman where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on iTunes or support it on Patreon https://www.patreon.com/lexfridman.

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Lex Fridman?

  The following is a conversation with Regina Barzle. She's a professor at MIT and a world-class researcher in natural language processing and applications of deep learning to chemistry and oncology, or the use of deep learning for early diagnosis, prevention, and treatment of cancer. She has also been recognized for a teaching of several successful AI-related courses at MIT, including the popular Introduction to Machine Learning course. This is the Artificial Intelligence Podcast. If you enjoy it, subscribe on YouTube, give it five stars on iTunes, support it on Patreon, or simply connect with me on Twitter at LexFriedman, spelled F-R-I-D-M-A-N.

• 0:43Lex Fridman?

  And now here's my conversation with Regina Barzle.

• 1:06Lex Fridman?

  In an interview, you've mentioned that if there's one course you would take, it would be a literature course with a friend of yours that a friend of yours teaches. Just out of curiosity, because I couldn't find anything on it, are there books or ideas that had profound impact on your life journey? Books and ideas perhaps outside of computer science and the technical fields?

• 1:28Speaker 01

  I think because I'm spending a lot of my time at MIT and previously in other institutions where I was a student, I have a limited ability to interact with people. So a lot of what I know about the world actually comes from books. And there were quite a number of books that had profound impact on me and how I view the world. Let me just give you one example of such a book. I've maybe a year ago read a book called The Emperor of All Melodies. It's a book about, it's kind of a history of science book on how the treatments and drugs for cancer were developed.

• 2:09Speaker 01

  That book, despite the fact that I am in the business of science, really opened my eyes on how imprecise and imperfect the discovery process is and how imperfect are current solutions. And what makes science succeed and be implemented? And sometimes it's actually not the strengths of the idea, but devotion of the person who wants to see it implemented. So this is one of the books that, you know, at least for the last year, quite changed the way I'm thinking about scientific process just from the historical perspective. And what do I need to do to make my ideas really implemented? Let me give you an example of a book,

• 2:53Speaker 01

  which is not a kind of, which is a fiction book. It's a book called Americana. And this is a book about a young female student who comes from Africa to study in the United States. And it describes her past, you know, within her studies and her life transformation that, you know, in a new country and kind of adaptation to a new culture. And when I read this book, I saw myself in many different points of it. But it also kind of gave me the lens on different events

• 3:37Speaker 01

  and some events that I never actually paid attention to. One of the funniest stories in this book is how she arrives to her new college and she starts speaking in English. And she had this beautiful British accent because that's how she was educated in her country. This is not my case. And then she notices that the person who talks to her, you know, talks to her in a very funny way, in a very slow way. And she's thinking that this woman is disabled and she's also trying to kind of to accommodate her. And then after a while, when she finishes her discussion with this officer from her college, she sees how she interacts with other students, with American students. And she discovers that actually...

• 4:25Speaker 01

  She talked to her this way because she saw that she doesn't understand English. And I thought, wow, this is a funny experience. And literally, within few weeks, I went to LA to a conference. And I asked somebody in the airport, you know, how to find like a cab or something. And then I noticed that this person is talking in a very strange way. And my first thought was that this person have some, you know, pronunciation issues or something. And I'm trying to talk very slowly to him. And I was with another professor, Ernst Frankel. And he's like laughing because it's funny that I don't get that the guy is talking in this way because he thinks that I cannot speak. So it was really kind of mirroring experience.

• 5:07Speaker 01

  And it let me think a lot about my own experiences moving, you know, from different countries. So I think that books play a big role in my understanding of the world.

• 5:19Lex Fridman?

  On the, on the science question, you mentioned that it made you discover that personalities of human beings are more important than perhaps ideas. Is that what I heard?

• 5:30Speaker 01

  It's not necessarily that they are more important than ideas, but I think that ideas on their own are not sufficient. And many times, at least at the local horizon, it's the personalities and their devotion to their ideas is really that locally changes the landscape. Now, if you're looking at AI, like, let's say, thirty years ago, you know, Dark Ages of AI or whatever, what is symbolic times, you can use any word. You know, there were some people, now we are looking at a lot of that work and we are kind of thinking this is not really maybe a relevant work. But you can see that some people managed to take it and to make it so shiny

• 6:12Speaker 01

  and dominate the, you know, the academic world and make it to be the standard. If you look at the area of natural language processing. It is well-known fact that the reason the statistics in NLP took such a long time to become mainstream, because there were quite a number of personalities which didn't believe in this idea and didn't stop research progress in this area. So I do not think that, you know, asymptotically maybe personalities matters, but I think locally it does make quite a bit of impact.

• 6:51Lex Fridman?

  Beautifully put, okay.

• 6:52Speaker 01

  And it generally, you know, speeds up the rate of adoption of the new ideas.

• 6:58Lex Fridman?

  Yeah, and the other interesting question is, in the early days of particular discipline, I think you mentioned in that book, is ultimately a book of cancer?

• 7:09Speaker 01

  It's called The Emperor of All Melodies.

• 7:11Lex Fridman?

  Yeah, and those melodies included the trying to the medicine, was it centered around?

• 7:17Speaker 01

  So it was actually centered on, you know, how people sort of curing cancer. Like, for me, it was really a discovery how people, what was the science of chemistry behind drug development, that it actually grew up out of dyeing, like coloring industry, that people who developed chemistry in 19th century in Germany and Britain to do, you know, the really new dyes, they looked at the molecules and identified that they do certain things to cells. And from there, the process started. And, you know, like historically, yeah, this is fascinating, that they managed to make the connection and look under the microscope

• 7:57Speaker 01

  and do all this discovery. But as you continue reading about it, and you read about how chemotherapy drugs, which were developed in Boston, and some of them were developed, and Farber, Dr. Farber from Donna Farber.

• 8:14Speaker 01

  You know how the experiments were done, that, you know, there was some miscalculation. Let's put it this way, and they tried it on the patients and they just, and those were children with leukemia and they died. And then they tried another modification. You look at the process, how imperfect is this process? And you know, like if we're again, looking back like six years ago, 70 years ago, you can kind of understand it. But some of the stories in this book, which were really shocking to me, were really happening, you know, maybe decades ago. And we still don't have a vehicle to do it much more fast and effective. And, you know, scientifically, the way I'm thinking, computer science, scientific.

• 8:55Lex Fridman?

  So from the perspective of computer science, you've got a chance to work the application to cancer and to medicine in general. From a perspective of an engineer and a computer scientist, how far along are we from understanding the human body? Biology of being able to manipulate it in a way we can cure some of the maladies, some of the diseases?

• 9:16Speaker 01

  So this is very interesting question. And if you're thinking as a computer scientist about this problem, I think one of the reasons that we succeeded in the areas we as a computer scientist succeeded is because we don't have, we are not trying to understand in some ways. Like if you're thinking about like e-commerce, Amazon, Amazon doesn't really understand you. And that's why it recommends you certain books or certain products, correct? And in, you know, traditionally, when people were thinking about marketing, you know, they divided the population to different kind of subgroups,

• 9:56Speaker 01

  identify the features of this subgroup and come up with a strategy which is specific to that subgroup. If you're looking about recommendations, you think they're not. Claiming that they're understanding somebody, they're just managing to, from the patterns of your behavior, to recommend you a product. Now, if you look at the traditional biology, and obviously, I wouldn't say that I am at any way, you know, educated in this field. But, you know, what I see, there is really a lot of emphasis on mechanistic understanding. And it was very surprising to me, coming from computer science, how much emphasis is on this understanding. And given the complexity of the system, maybe the deterministic full understanding

• 10:40Speaker 01

  of these processes is, you know, beyond our capacity. And the same way as in computer science, when we're doing recognition, when you're doing recommendation, and many other areas, it's just probabilistic matching process. And in some way, maybe in certain cases, we shouldn't even attempt to understand. Or we can attempt to understand, but in parallel, we can actually do this kind of matching that would help us to find hero, to do early diagnostics, and so on. And I know that in these communities, it's really important to understand. But I'm sometimes wondering, what exactly does it mean to understand here?

• 11:20Lex Fridman?

  Well, there's stuff that works, and, but that can be, like you said, separate from this deep human desire to uncover the mysteries of the universe, of, of science, of the way the body works, the way the mind works. It's the dream of symbolic AI, of being able to reduce human knowledge into, into logic, and be able to play with that logic in a way that's very explainable and understandable for us humans. I mean, that's a beautiful dream. So I understand it. But it seems that what seems to work today, and we'll talk about it more, is as much as possible, reduce stuff into data, reduce whatever problem you're interested in to data, and try to apply statistical methods,

• 12:04Lex Fridman?

  apply machine learning to that. On a personal note, you were diagnosed with breast cancer in 2014.

• 12:12Lex Fridman?

  What did facing your mortality make you think about? How did it change you?

• 12:17Speaker 01

  You know, this is a great question. And I think that I was interviewed many times and nobody actually asked me this question. I think I was forty-three at a time. And it the first time I realized in my lifetime I may die. And I never thought about it before. And yeah, and there was a long time since you diagnosed until you actually know what you have and how to see if it is your disease. For me, it was like maybe two and a half months. And I didn't know where I am during this time because I was getting different tests. And one would say it's bad and I would say, no, it is not. So until I knew where I am, I really was thinking about all these different possible outcomes.

• 12:55Lex Fridman?

  Were you imagining the worst? Or were you trying to be optimistic?

• 12:58Speaker 01

  It would be really, I don't remember, you know, what was my thinking. It was really a mixture with many components at the time, speaking, you know, in our terms. And one thing that I remember, and you know, every test comes and then you think, oh, it could be this, so it may not be this. And you're hopeful and then you're desperate. So it's like there is a whole, you know, slew of emotions that goes through you. But what I remember is that when I came back to MIT, I was kind of going the whole time through the treatment to MIT, but my brain was not really there. But when I came back, really finished my treatment and I was here teaching and everything,

• 13:41Speaker 01

  you know, I look back at what my group was doing, what other groups was doing. And I saw these trivialities. It's like people are building their careers on improving some percent, around two or three percent or whatever. I was like, seriously, I did a work on how to decipher Ugaritic, like a language that nobody speak and whatever, like what is significance? When all of a sudden, you know, I walked out of MIT, which is, you know, when people really do care, you know, what happened to your A clear paper, you know, what is your next publication to ACL, to the world where people, you know, people, you see a lot of suffering that I'm kind of totally shielded on it on daily basis. And it's like the first time I've seen like real life and real suffering.

• 14:26Speaker 01

  And I was thinking, why are we trying to improve the parser? Or deal with trivialities when we have capacity to really make change? And it was really challenging to me because on one hand, you know, I have my graduate students who really want to do their papers and their work. And they want to continue to do what they were doing, which was great. And then it was me who really kind of reevaluated what is the importance? And also at that point, because I had to take some break,

• 14:59Speaker 01

  I look back into like my years in science. And I was thinking, you know, like 10 years ago, this was the biggest thing. I don't know, topic models, we have like millions of papers on topic models and variation of topics models. Now it's totally like irrelevant. And you you you start looking at this, you know, what do you perceive as important at different point of time? And how, you know, it fades over time. And since we have a limited time, all of us have limited time on us. It's really important to prioritize things that really matter to you, maybe matter to you at that particular point. But it's important to take some time and understand what matters to you,

• 15:44Speaker 01

  which may not necessarily be the same as what matters to the rest of your scientific community and pursue that vision.

• 15:51Lex Fridman?

  So though that moment, did it make you cognizant? You mentioned suffering of just the general amount of suffering in the world. Is that what you're referring to? So as opposed to topic models and specific detailed problems in NLP, did did you start to think about other people who have been diagnosed with cancer? Is that the way you saw the started to see the world perhaps?

• 16:17Speaker 01

  Oh, absolutely. And it actually creates because like, for instance, you know, there is parts of the treatment where you need to go to the hospital every day. And you see, you know, the community of people that you see, and many of them are much worse than I I was at a time. And You're all of a sudden see it all. And people who are happier someday just because they feel better. And for people who are in our normal realm, you take it totally for granted that you feel well, that if you decide to go running, you can go running. And you can, you know, you're pretty much free to do whatever you want with your body. Like, I saw like a community, my community became those people.

• 17:00Speaker 01

  And I remember one of my friends, Dina Katabi, took me to Prudential to buy me a gift for my birthday. And it was like the first time in months that I went to kind of to see other people. And I was like, wow. First of all, these people, you know, they are happy and they are laughing and they're very different from this other my people. And second thing, are they totally crazy? They're like laughing and wasting their money on some stupid gifts. And, you know, they may die. They already may have cancer and they don't understand it. So you can really see how the mind changes, that you can see that, you know, before that you can ask, didn't you know that you're gonna die? Of course I knew, but it was a kind of a theoretical notion.

• 17:45Speaker 01

  It wasn't something which was concrete. And at that point, when you really see it and see how little means sometime the system has to help them, you really feel that we need to take a lot of our brilliance that we have here at MIT and translate it into something useful.

• 18:05Lex Fridman?

  Yeah, and useful can have a lot of definitions, but of course alleviating, suffering alleviating. Trying to cure cancer is a beautiful mission. So I of course know theoretically the notion of cancer, but just reading more and more about it, 1.7 million new cancer cases in the United States every year, 600,000 cancer-related deaths every year. So this has a huge impact, United States globally. When broadly, before we talk about how machine learning, how MIT can help, when do you think we as a civilization will cure cancer?

• 18:49Lex Fridman?

  How hard of a problem is it from everything you've learned from it recently?

• 18:54Speaker 01

  I cannot really assess it. What I do believe will happen with the advancement in machine learning, that a lot of types of cancer, we will be able to predict way early and more effectively utilize existing treatments. I think, I hope at least, that with all the advancements in AI and drug discovery, we would be able to much faster find relevant molecules. What I'm not sure about is how long it will take the medical establishment and regulatory bodies to kind of catch up and to implement it. And I think this is a very big piece of puzzle that is currently not addressed.

• 19:37Lex Fridman?

  That's a really interesting question. So first, a small detail, and I think the answer is yes. But is cancer one of the diseases that when detected earlier, that significantly improves the outcomes? Because we will talk about there's the cure, and then there is detection. And I think where machine learning can really help is earlier detection. So does detection help?

• 20:05Speaker 01

  Detection is crucial. For instance, the vast majority of pancreatic cancer patients are detected at the stage that they are incurable. That's why they have such a terrible survival rate. It's like just few percent over five years. It's pretty much today the sentence. But if you can discover this disease early, there are mechanisms to treat it. And in fact, I know a number of people who were diagnosed and saved just because they had food poisoning. They had terrible food poisoning. They went to ER, they got scanned. There were early signs on the scan, and that what saved their lives.

• 20:50Speaker 01

  But this wasn't really an accidental case. So as we become better, we would be able to help to many more people that are likely to develop diseases. And I just want to say that As I got more into this field, I realized that, you know, cancer is of course terrible disease, but there are really the whole slew of terrible diseases out there, like neurodegenerative diseases and others. So we, of course, a lot of us are fixated on cancer just because it's so prevalent in our society and you see these people, and there are a lot of patients with neurodegenerative diseases and the kind of aging diseases that we still don't have a good solution for.

• 21:34Speaker 01

  And we, you know, and I felt as a computer scientist, we kind of decided that it's other people's job to treat these diseases, because it's like traditionally, people in biology or in chemistry or M.D.s are the ones who are thinking about it. And after kind of start paying attention, I think that it's really a wrong assumption and we all need to join the battle.

• 21:59Lex Fridman?

  So how, it seems like in cancer specifically, that there's a lot of ways that machine learning can help. So what's, what's the role of machine learning in the diagnosis of cancer?

• 22:11Speaker 01

  So for many cancers today, we really don't know what is your likelihood to get cancer. And for the vast majority of patients, especially on the younger patients, it really comes as a surprise. Like for instance, for breast cancer, eighty percent of the patients are first in their families, it's like me. And I never saw that I had any increased risk because, you know, nobody had it in my family and for some reason in my head, it was kind of inherited disease. But even if I would pay attention, the, the models that currently, these very simplistic statistical models that are currently used in clinical practice, it really don't give you an answer, so you don't know.

• 22:54Speaker 01

  And the same true for pancreatic cancer, the same true for non-smoking lung cancer and many others. So what machine learning can do here is utilize all this data to tell us Ellie, who is likely to be susceptible and using all the information that is already there, be it imaging, be it your other tests and, you know, eventually liquid biopsies and others, where the signal itself is not sufficiently strong for human eye to do good discrimination, because the signal may be weak, but by combining many sources, a machine which is trained on large volumes of data can really detect it early.

• 23:37Speaker 01

  And that's what we've seen with breast cancer and people are reporting it in other diseases as well.

• 23:43Lex Fridman?

  That really boils down to data, right? And in the different kinds of sources of data. And you mentioned regulatory challenges. So what are the challenges in gathering large data sets in this space?

• 23:58Speaker 01

  Again, another great question. So it took me after I decided that I want to work on it two years to get access to data.

• 24:05Lex Fridman?

  Any data, like any significant?

• 24:07Speaker 01

  Any significant amount. Like right now, in this country, there is no publicly available data set of modern mammograms that you can just go on your computer, sign a document and get it. It just doesn't exist. I mean, and obviously, every hospital has its own collection of mammograms. There are data that come out, that came out of clinical trials. But we're talking about you as a computer scientist who just want to run his or her model and see how it works. This data, like ImageNet, doesn't exist. And there is an set, which is called like Florida data set, which is a film mammogram from 90s, which is totally not representative of the current developments. Whatever you're

• 24:51Speaker 01

  learning on them doesn't scale up. This is the only resource that is available. And today, there are many. Agencies that govern access to data, like the hospital holds your data and the hospital decides whether they would give it to the researcher to work with this data or not.

• 25:09Lex Fridman?

  An individual hospital?

• 25:11Speaker 01

  Yeah, I mean, the hospital may, you know, assuming that you're doing research collaboration, you can submit, you know, there is a proper approval process guided by IRB. And you, if you go through all the processes, you can eventually get access to the data. But if you yourself know our AI community, there are not that many people who actually ever got access to data because it's a very challenging process.

• 25:37Lex Fridman?

  And sorry, just a quick comment, MGH or any kind of hospital, are they scanning the data? Are they digitally storing it?

• 25:46Speaker 01

  Oh, it is already digitally stored. You don't need to do any extra processing steps. It's already there in the right format. Is that right now, there are a lot of issues that govern access to the data because the hospital is legally responsible for, for the data. And, you know, they have a lot to lose if they give the data to the wrong person, but they may not have a lot to gain if they give it as a hospital, as a legal entity, as giving it to you. And the way, you know, what I would imagine happening in the future is the same thing that happens when you're getting your driving license. You can decide whether you want to donate your organs.

• 26:27Speaker 01

  You can imagine that whenever a person goes to the hospital, they, it should be easy for them to donate their data for research. And it can be different kind of, do they only give you test results or only mammogram, or only imaging data or the whole medical record?

• 26:44Speaker 01

  Because at the end, we all will benefit from all this insight. And it's not like you say, I want to keep my data private, but I would really love to get it, you know, from other people because other people are thinking the same way. So. If there is a mechanism to do this donation and the patient has an ability to say how they want to use their data for research, it would be really a game changer.

• 27:11Lex Fridman?

  People, when they think about this problem, there's a, it depends on the population, it depends on the demographics, but there's some privacy concerns generally, not just medical data, just any kind of data. It's what you said, my data, it should belong kind of to me. I'm worried how it's going to be misused. How do we alleviate those concerns? Because that seems like a problem that needs to be, that problem of trust, of transparency, needs to be solved before we build large data sets that help detect cancer, help save those very people in the future.

• 27:47Speaker 01

  So I think there are two things that could be done. There is a technical solutions and there are societal solutions. So on the technical end, we today have ability to improve this ambiguity. Like for instance, for imaging, it's, you know, for imaging, you can do it pretty well.

• 28:12Lex Fridman?

  What's this ambiguity?

• 28:13Speaker 01

  And this, sorry, this, removing the identification, removing the names of the people. There are other data, like if it is a raw text, you cannot really achieve 99.9%. But there are all these techniques that actually some of them are developed at MIT. How you can do learning on the encoded data where you locally encode the image, you train a network which only works on the encoded, on encoded images and then you send the outcome back to the hospital and you can open it up. So those are the technical solution. There are a lot of people who are working in this space where the learning happens in the encoded form. We are still early, but this is an interesting research area

• 28:56Speaker 01

  where I think we'll make more progress. There is a lot of work in natural language processing community, how to do the identification better.

• 29:07Speaker 01

  But even today, there are already a lot of data which can be identified perfectly, like your test data, for instance, correct? Where you can just, you know, the name of the patient, you just want to extract the part with the numbers. The big problem here is, again, hospitals don't see much incentive to give this data away, on one hand, and then there is general concern. Now, when I'm talking about societal benefits and about the education, the public needs to understand, and I think that there are situations, and I still remember myself, when I really needed an answer, I had to make a choice.

• 29:50Speaker 01

  There was no information to make a choice, you're just guessing. And at that moment, you feel that your life is at the stake, but you just don't have information to make the choice. And many times when I give talks, I get emails from women who say, you know, "I'm in this situation, can you please run statistics and see what are the outcomes?" We get almost every week a mammogram that comes by mail to my office at MIT, I'm serious, that people ask to run because they need to make, you know, life-changing decisions. And of course, you know, I'm not planning to open a clinic here, but we do run and give them the results for their doctors.

• 30:33Speaker 01

  But the point that I'm trying to make, that we all, at some point, or our loved ones, will be in the situation where you need information to make the best choice. And if this information is not available, you would feel vulnerable and unprotected. And then the question is, you know, what do I care more? Because at the end, everything is a trade-off, correct?

• 30:57Lex Fridman?

  Yeah, exactly. Just out of curiosity, what, it seems like one possible solution, I'd like to see what you think of it.

• 31:06Lex Fridman?

  Based on what you just said, based on wanting to know answers for when you're yourself in that situation, is it possible for patients to own their data as opposed to hospitals owning their data? Of course theoretically, I guess, patients own their data, but can you walk out there with a USB stick containing everything or upload it to the cloud where a company, you know, I remember Microsoft had a service like I try, I was really excited about and Google Health was there. I tried to give, I was excited about it. Basically, companies helping you upload your data to the cloud so that you can move from hospital to hospital, from doctor to doctor. Do you see a promise of that kind of possibility?

• 31:49Speaker 01

  I absolutely think this is, you know, the right way to to exchange the data. I don't know now who's the biggest player in this field, but I can clearly see that even, you know, for even for totally selfish health reasons, when you are going to a new facility and many of us are sent to some specialized treatment, they don't easily have access to your data. And today, you know, we might want to send a smarmgram, need to go to their hospital, find some small office which gives them the CD and the ship as a CD. So you can imagine we're looking at kind of decades old mechanism of data exchange.

• 32:28Speaker 01

  So I definitely think this is an area where hopefully all the right regulatory and technical forces will align and we will see it actually implemented.

• 32:40Lex Fridman?

  It's sad because unfortunately, and I have, I need to research why that happened, but I'm pretty sure Google Health and Microsoft Health Vault, or whatever it's called, both closed down, which means that there was either regulatory pressure, or there's not a business case, or there was challenges from hospitals, which is very disappointing. So when you say you don't know what the biggest players are, the two biggest that I was aware of closed their doors. So I'm hoping, I'd love to see why, and I'd love to see who else can come up. It seems like a, one of those Elon Musk style problems that are obvious, needs to be solved, and somebody needs to step up and actually do this large scale data, you know, data collection.

• 33:24Speaker 01

  I know there is an initiative in Massachusetts, a thing actually led by the governor, to try to create this kind of health exchange system, where at least to help people who kind of when you show up in emergency room and there is no information about what are your allergies and other things. So I don't know how far it will go. But another thing that you said, and I find it very interesting, is actually who are the successful players in this space and the whole implementation, how does it go? To me, this, from the anthropological perspective, it's more fascinating that AI that today goes in healthcare, you know, we've seen so many, you know, attempts and so very little successes. And it's interesting

• 34:08Speaker 01

  to understand that I by no means, you know, have knowledge to assess it, why we are in the position where we are.

• 34:16Lex Fridman?

  Yeah, it's interesting because data is really fuel for a lot of successful applications. And when that data acquires regulatory approval, like the FDA or any kind of approval, it's seems that the computer scientists are not quite there yet in being able to play the regulatory game, understanding the fundamentals of it.

• 34:38Speaker 01

  I think that in many cases, when even people do have data, we still don't know what exactly do you need to demonstrate to change the standard of care. Like, let me give you an example related to my breast cancer research. So traditional, in traditional breast cancer risk assessment, there is something called density, which determines the likelihood of a woman to get cancer. And this is pretty much says how much white do you see on the mammogram? The white it is, the more likely the tissue is dense. And the idea behind density,

• 35:19Speaker 01

  it's not a bad idea. In 1967, a radiologist called Wolf decided to look back at women who were diagnosed and see what is special in their images. Can we look back and say that they are likely to develop? So he come up with some patterns. And it was the best that his human eye can, you know, can identify. Then it was kind of formalized and coded into four categories. And that's what we are using today. And today, this density assessment is actually a federal law from 2019, approved by President Trump and for the previous FDA commissioner,

• 35:57Speaker 01

  where women are supposed to be advised by their providers if they have high density, putting them into high-risk category. And in some states, you can actually get supplementary screening paid by your insurance because you're in this category. Now, you can say, how much science do we have behind it? Whatever, biological science or epidemiological evidence. So it turns out that between 40 and 50% of women have dense breasts. So above 40% of patients are coming out of their screening, and somebody tells them, you are in high risk.

• 36:31Lex Fridman?

  High risk.

• 36:32Speaker 01

  Now, what exactly does it mean if you, as half of the population, in high risk? It's like, maybe I'm not, you know? Or what do I really need to do with it? Because the system doesn't provide me a lot of the solutions, because there are so many people like me. We cannot really provide very expensive solutions for them. And the reason this whole density became this big deal, it's actually advocated by the patients who felt very unprotected, because many women went, did the mammograms, which went normal. And then it turns out that they already had cancer, quite developed cancer. So they didn't have a way to know who is really at risk and what is the likelihood that when the doctor tells you, you're okay, you're not okay.

• 37:15Speaker 01

  So at the time, and it was, you know, 15 years ago, this maybe was the best piece of science that we had. And it took, you know, quite 15, 16 years to make it federal law. But now that this is, this is a standard. Now, with a deep learning model, we can so much more accurately predict who is going to develop breast cancer just because you're trained on a large thing. And instead of describing how much white and what kind of white machine can systematically identify the patterns, which was the original idea behind the sort of the radiologist machines, can do it much more systematically and predict the risk when you're training the machine to look at the image and to say the risk in one, two, five years.

• 37:59Speaker 01

  Now, you can ask me how long it will take to substitute this density, which is broadly used across the country and really is not helping.

• 38:09Speaker 01

  To bring these new models. And I would say it's not a matter of the algorithm. Algorithm is already orders of magnitude better than what is currently in practice. I think it's really the question, who do you need to convince? How many hospitals do you need to run the experiment? What, you know, all this mechanism of adoption? And how do you explain to patients and to women across the country? That this is really a better measure. And again, I don't think it's an AI question. We can work more and make the algorithm even better. But I don't think that this is the current, you know, the barrier. The barrier is really this other piece that for some reason is not really explored. It's like anthropological piece.

• 38:54Speaker 01

  And coming back to your question about books, there is a book that I'm reading. It's called American Sickness by Elizabeth Rosenthal. And I got this book from my clinical collaborator, Dr. Conny Lehman. And I sort of know everything that I need to know about American health system. But you know, every page doesn't fail to surprise me. And I think there is a lot of interesting and really deep lessons for people like us from computer science who are coming into this field to really understand how complex is the system of incentives in the system to understand how you really need to play to drive adoption.

• 39:36Lex Fridman?

  You just said it's complex, but if we're trying to simplify it, who do you think most likely would be successful if we push on this group of people? Is it the doctors? Is it the hospitals? Is it the governments or policymakers? Is it the individual patients, consumers?

• 39:56Lex Fridman?

  Who needs to be inspired to most likely lead to adoption? Or is there no simple answer?

• 40:04Speaker 01

  There's no simple answer, but I think there is a lot of good people in medical system who do want, you know, to make a change. And I think a lot of power will come from us as a consumers, because we all are consumers or future consumers of healthcare services. And

• 40:26Speaker 01

  I think we can do so much more in explaining the potential and not in the hype terms and not saying that we now cured Alzheimer and, you know, I'm really sick of reading these kind of articles which make these claims. But really to show with some examples what this implementation does and how it changes the care. Because I can't imagine, it doesn't matter what kind of politician it is, you know, we all are susceptible to these diseases. There is no one who is free. And eventually, you know, we all are humans and we are looking for ways to alleviate the suffering. And this is one possible way where we currently are underutilizing, which I think can help.

• 41:07Lex Fridman?

  So it sounds like the biggest problems are outside of AI in terms of the biggest impact at this point. But are there any open problems in the application of ML to oncology in general? So improving the detection or any other creative methods, whether it's on the detection, segmentation, sort of the vision perception side, or some other clever inference? Yeah, what in general, in your view, are the open problems in this space?

• 41:37Speaker 01

  See, I just want to mention that beside detection, another area where I am kind of quite active and I think it's really an increasingly important area in healthcare is drug design.

• 41:47Lex Fridman?

  Absolutely.

• 41:50Speaker 01

  Because, you know, it's fine if you detect something early, but you still need to get, you know, to get drugs and new drugs for these conditions. And today, all of the drug design, ML is non-existent there. We don't have any drug that was developed by the ML model or even not developed, but at least even knew that ML model plays some significant role. I think this area with all the new ability to generate molecules with desired properties to do in silic screening is really a big open area. To be totally honest with you, you know, when we are doing diagnostics and imaging,

• 42:32Speaker 01

  primarily taking the ideas that were developed for other areas and you applying them with some adaptation, the area of, you know...

• 42:41Speaker 01

  Drug design is really technically interesting and exciting area. You need to work a lot with graphs and capture various 3D properties. There are lots and lots of opportunities to be technically creative. And I think there are a lot of open questions in this area. You know, we're already getting a lot of successes even, you know, with a kind of the first generation of these models. But there is much more new creative things that you can do. And what's very nice to see is that actually, you know, the more powerful, the more interesting models actually do do better.

• 43:22Speaker 01

  So there is a place to innovate in machine learning in this area. And some of these techniques are really unique to, let's say, to, you know, graph generation and other things.

• 43:36Lex Fridman?

  So. What, just to interrupt really quick, I'm sorry. Graph generation or graphs, drug discovery in general. What's, how do you discover a drug? Is this chemistry? Is this trying to predict different chemical reactions? Or is it some kind of, what do graphs even represent in this space?

• 43:59Speaker 01

  Oh, sorry, sorry.

• 44:01Lex Fridman?

  And what's a drug?

• 44:02Speaker 01

  Okay, so let's say you're thinking there are many different types of drugs. But let's say you're going to talk about small molecules. Because I think today, the majority of drugs are small molecules. So small molecule is a graph. The molecule is just where the node in the graph is an atom. And then you have the bone. So it's really a graph representation if you're looking at it in 2D, correct?

• 44:22Lex Fridman?

  Yeah.

• 44:22Speaker 01

  You can do it 3D, but let's say, well, let's keep it simple and stick in 2D. So pretty much my understanding today, how it is done at scale in the companies, you're without machine learning. You have high throughput screening. So you know that you are interested to get certain biological activity of the compound. So you scan a lot of compounds, like maybe hundreds of thousands, some really big number of compounds. You identify some compounds which have the right activity. And then at this point, you know, the chemists come and they're trying to, now to optimize this original heat to different properties that you want it to be maybe soluble. You want to decrease toxicity.

• 45:06Speaker 01

  You want to decrease the side effects.

• 45:08Lex Fridman?

  Are those, sorry, again to drop, can that be done in simulation or just by looking at the molecules? Or do you need to actually run reactions in real labs with lab coats and stuff?

• 45:19Speaker 01

  So when you do high throughput screening, you really do screening, it's in the lab. It's really the lab screening, you screen the molecules, correct?

• 45:28Lex Fridman?

  I don't know what screening is.

• 45:29Speaker 01

  The screening is just check them for certain property.

• 45:32Lex Fridman?

  Like in the physical space, in the physical world, like actually there's a machine probably that's doing some, that's actually running the reaction.

• 45:38Speaker 01

  Actually running the reactions, yeah. So there is a process where you can run, and that's why it's called high throughput, that it becomes cheaper and faster to do it on very big number of molecules. You run the screening, you identify potential, you know, potential good starts. And then where the chemists come in, who, you know, have done it many times, and then they can try to look at it and say, how can you change the molecule to get the desired profile in terms of all other properties? So maybe how do I make it more bioactive and so on? And there, you know, the creativity of the chemist really is the one that determines

• 46:19Speaker 01

  the success of this design, because again, they have a lot of domain knowledge of, you know, what works, how do you decrease toxicity and so on? And that's what they do. So all the drugs that are currently, you know, in the FDA approved drugs, or even drugs that are in clinical trials, they are designed using these domain experts, which goes through this combinatorial space of molecules or graphs or whatever, and find the right one or adjust it to be the right ones.

• 46:52Lex Fridman?

  Sounds like the the the breast density heuristic from sixty seven, the same echoes.

• 46:57Speaker 01

  It's not necessarily that, it's really, you know, it's really driven by deep understanding, it's not like they just observe it. I mean, they do deeply understand chemistry and they do understand how different groups and how does it changes the properties. So there is a lot of science that gets into it and a lot of kind of simulation, how do you want it to behave?

• 47:19Speaker 01

  It's very, very complex.

• 47:21Lex Fridman?

  So they're quite effective at this design, obviously.

• 47:23Speaker 01

  Now, effective, yeah, we have drugs. Like, depending on how do you measure effective? If you measure it in terms of cost, it's prohibitive. If you measure it in terms of times, you know, we have lots of diseases for which we don't have any drugs and we don't even know how to approach. I don't need to mention few drugs or degenerative disease drugs that fail, you know. So there are lots of, you know, trials that fail, you know, in later stages, which is really catastrophic from the financial perspective. So, you know, is it the effective, the most effective mechanism? Absolutely no, but this is the only one that currently works.

• 48:01Speaker 01

  And I would, you know, I was closely interacting with people in pharmaceutical industry. I was really fascinated on how sharp and what a deep understanding of the domain do they have? It's not observation driven. There is really a lot of science behind what they do. But if you ask me, can machine learning change it? I firmly believe yes. Because even the most experienced chemists cannot, you know, hold in their memory and understanding everything that you can learn, you know, from millions of molecules and reactions. And

• 48:34Lex Fridman?

  And the space of graphs is a totally new space. I mean, it's a really interesting space for machine learning to explore, graph generation.

• 48:41Speaker 01

  Yeah, so there are a lot of things that you can do here. So we do a lot of work. So the first tool that we started with was the tool that can predict properties of the molecules. So you can just give the molecule and the property. It can be bioactivity property or it can be some other property. And you train the molecules and you can now take a new molecule and predict this property. Now, when people started working in this area, it is something very simple. They do kind of existing, you know, fingerprints, which is kind of handcrafted features of the molecule. When you break the graph to substructures and then you run a feedforward neural network. And what was interesting to see that clearly,

• 49:25Speaker 01

  you know, this was not the most effective way to proceed. And you need to have much more complex models that can induce a representation, which can translate this graph into the embeddings and do these predictions. So this is one direction. Then another direction, which is kind of related, is not only to stop by looking at the embedding itself, but actually modify it to produce better molecules. So you can think about it as machine translation, that you can start with a molecule, and then there is an improved version of molecule. And you can again, with encoder, translate it into the hidden space and then learn how to modify to improve the in some ways version of the molecules. So that's, it's kind of really exciting.

• 50:09Speaker 01

  We already have seen that the property prediction works pretty well. And now we are generating molecules. And there is actually labs which are manufacturing this molecule. So we'll see where it will get us.

• 50:23Lex Fridman?

  Okay, that's really exciting. There's a lot of promise. Speaking of machine translation and embeddings, you have done a lot of really great research in NLP, natural language processing.

• 50:36Lex Fridman?

  Can you tell me your journey through NLP? What ideas, problems, approaches were you working on? Were you fascinated with? Did you explore before this magic of deep learning reemerged and after?

• 50:51Speaker 01

  So when I started from my work in NLP, it was in 97. This is very interesting time. It was exactly the time that I came to ACL. At the time, I could barely understand English. But it was exactly like the transition point. Because half of the papers were really, you know, rule-based approaches, where people took more kind of heavy linguistic approaches for small domains and tried to build up from there. And then there were the first generation of papers, which were corpus-based papers. And they were very simple in our terms. When you collect some statistics and do prediction based on them. But I found it really fascinating that, you know, one community can think so very differently about, you know, about the problem.

• 51:36Speaker 01

  And I remember my first paper that I wrote, it didn't have a single formula. It didn't have evaluation, it just had examples of outputs. And this was a standard of the field at the time. In some ways, I mean, people maybe just started emphasizing the empirical evaluation. But for many applications like summarization, you just wrote some examples of outputs. And then increasingly, you can see that how the statistical approaches dominated the field. And we've seen, you know, increased performance across many basic tasks. The third part of the story may be that if you look again through this journey,

• 52:18Speaker 01

  we see that the role of linguistics in some ways greatly diminishes. And I think that you really need to look through the whole proceeding to find one or two papers, which make some interesting linguistic references.

• 52:34Lex Fridman?

  You mean today?

• 52:35Speaker 01

  Today, today. This was definitely.

• 52:37Lex Fridman?

  Things like syntactic trees, just even basically against our conversation about human understanding of language, which I guess what linguistics would be, structured, hierarchical, representing language in a way that's human explainable, understandable is missing today.

• 52:56Speaker 01

  I don't know if it is what is explainable and understandable. At the end, you know, we perform functions and it's okay to have a machine which performs a function. Like when you're thinking about your calculator, correct? Your calculator can do calculation very different from you who do the calculation, but it's very effective in it. And this is fine if we can achieve certain tasks with high accuracy. It doesn't necessarily mean that it has to understand it the same way as we understand. In some ways, it's even naive to request because you have so many other sources of information that are absent when you are training your system. So it's okay, they deliver it. And I would tell you one application that's just really fascinating.

• 53:39Speaker 01

  In 97, when I came to ACL, there were some papers on machine translation. They were like primitive, like people were trying really, really simple. And. The feeling, my feeling was that to make real machine translation systems, it's like to fly at the moon and build a house and a garden and live happily ever after. I mean, it's like impossible. I never could imagine that within, you know, 10 years, we would already see the system working. And now, you know, nobody is even surprised to utilize this system on daily basis. So this was like a huge, huge progress, saying that people for a very long time tried to solve using other mechanisms and they were unable to solve it. That's why, coming back to a question about biology,

• 54:23Speaker 01

  that in linguistics, people tried to go this way and tried to write the syntactic trees and tried to abstract it and to find the right representation. And, you know, they couldn't get very far with this understanding, while these models, using, you know, other sources, actually capable to make a lot of progress. Now, I'm not naive to think that we are in this paradise space in NLP. And I'm sure as you know, that when we slightly change the domain and when we decrease the amount of training, it can do like really bizarre and funny thing. But I think it's just a matter of improving generalization capacity, which is just a technical question.

• 55:08Lex Fridman?

  Wow. So that's, that's the question. How much of language understanding can be solved with deep neural networks? In your intuition, I mean, it's unknown, I suppose. But as we start to creep towards romantic notions of the spirit of the Turing test and conversation and dialogue and something that maybe to me or to us, so humans feels like it needs real understanding, how much can I be achieved with these neural networks or statistical methods?

• 55:44Speaker 01

  So I guess I am very much driven by the, by the outcomes. Can we achieve the performance which would be satisfactory for us for different tasks? Now, if you again look at machine translation systems, which are, you know, trained on large amounts of data, they really can do a remarkable job relatively to where they've been a few years ago. And if you, you know, if you project into the future, if it will be the same speed of improvement.

• 56:15Speaker 01

  You know, this is great. Now, does it bother me that it's not doing the same translation as we are doing now? If you go to cognitive science, we still don't really understand what we are doing. I mean, there are a lot of theories. There is obviously a lot of progress in studying, but our understanding, what exactly goes on, you know, in our brains when we process language is still not crystal clear and precise that we can translate it into machines. What does bother me is that, you know, again, that machines can be extremely brittle when you go out of your comfort zone of the, when there is a distributional shift between training and testing. And it have been years and years. Every year when a teacher in LP class, you know, show them some examples of translation

• 57:00Speaker 01

  from some newspaper in Hebrew or whatever. It was perfect. And then I have a recipe that Tommy Yakalos' system sent me a while ago, and it was written in Finnish of Carillion pies. And it's just a terrible translation. You cannot understand anything what it does. It's like some syntactic mistakes. It's just terrible. And year after year, I tried it on Google Translate. And year after year, it does this terrible work because I guess, you know, the recipes are not big part of their training repertoire.

• 57:32Lex Fridman?

  So, but in terms of outcomes, that's a really clean, good way to look at it. I guess the question I was asking is, do you think, imagine a future, do you think the current approaches can pass the Turing test in the way, in the best possible formulation of the Turing test? It's just, would you want to have a conversation with a neural network for an hour?

• 57:59Speaker 01

  Oh, God, no. No, there are not that many people that I would want to talk for an hour.

• 58:05Lex Fridman?

  But there are some people in this world, alive or not, that you would like to talk to for an hour. Could a neural network have achieved that outcome?

• 58:13Speaker 01

  So I think it would be really hard to create a successful training set, which would enable it to have a conversation for an hour, a contextual conversation for an hour.

• 58:23Lex Fridman?

  You think it's a problem of data, perhaps?

• 58:25Speaker 01

  I think in some ways it's a problem of data. It's a problem both of data and the problem of the way we're training our systems, their ability to truly to generalize, to be very compositional. In some ways, it limited, you know, in the current capacity, at least.

• 58:42Speaker 01

  You know, we can translate well, we can, you know, find information well, we can extract information. So there are many capacities in which it's doing very well. And you can ask me, would you trust the machine to translate for you and use it as a source? I would say absolutely, especially if we're talking about newspaper data or other data, which is in the realm of its own training set. I would say yes. But, you know, having conversations with a machine, it's not something that I would choose to do. But, you know, I would tell you something, talking about Turing test and about all this kind of ELIZA conversations. I remember visiting Tencent in China and they have this chat board and they claim that

• 59:24Speaker 01

  there is like really humongous amount of the local population, which like for hours talks to the chat board. To me, it was, I cannot believe it, but apparently it's like documented that there are some people who enjoy this conversation. And, you know, it brought to me the, another MIT story about ELIZA and Weizengbaum. I don't know if you're familiar with the story. So Weizengbaum was a professor at MIT and when he developed this ELIZA, which was just doing string matching, very trivial, like restating of what you said with very few rules, no syntax. Apparently there were secretaries at MIT that would sit for hours and converse with this trivial thing. And at the time, there was no beautiful interfaces.

• 1:00:07Speaker 01

  So you actually need to go through the pain of communicating. And Weizengbaum himself was so horrified by this phenomenon that people can't believe enough to the machine, you just need to give them the hint that machine understands you and you can complete the rest. So he kind of stopped this research and went into kind of trying to understand what this artificial intelligence can do to our brains. So my point is, you know, how much, it's not how good is the technology, it's how ready we are to believe that it delivers the good that we are trying to get.

• 1:00:42Lex Fridman?

  That's a really beautiful way to put it. I, by the way, I'm not horrified by that possibility, but inspired by it because, I mean, human connection, whether it's through language or through love, it, it seems like it's very amenable to machine learning and the rest is just.

• 1:01:04Lex Fridman?

  Challenges of psychology, like you said, the secretaries who enjoy spending hours. I would say I would describe most of our lives as enjoying spending hours with those we love for very silly reasons. All we're doing is keyword matching as well. So I'm not sure how much intelligence we exhibit to each other with the people we love that we're close with. So it's a very interesting point of what it means to pass the Turing test with language. I think you're right. In terms of conversation, I think machine translation is, has very clear performance and improvement, right? What it means to have a fulfilling conversation is very, very person dependent and context

• 1:01:49Lex Fridman?

  dependent and so on. That's, yeah, it's very well put. But in your view, what's a benchmark in natural language, a test that's just out of reach right now, but we might be able to, that's exciting? Is it in machine, isn't perfecting machine translation? Or is there other, is it summarization? What's out there?

• 1:02:10Speaker 01

  I think it goes across specific application. It's more about the ability to learn from few examples for real, what we call few-shot learning and all these cases. Because, you know, the way we publish these papers today, we say, if we have, like naively, we get 55, but now we had a few example and we can move to 65. None of these methods actually realistically doing anything useful. You cannot use them today. And the ability to be able to generalize and to move or to be autonomous in finding the data that you need to learn, to be able to perfect new task or new language. This is an area where I think we really need.

• 1:02:56Speaker 01

  To move forward to, and we are not yet there.

• 1:03:00Lex Fridman?

  Are you at all excited, curious by the possibility of creating human-level intelligence?

• 1:03:07Lex Fridman?

  Is this, because you've been very, in your discussion, so if we're looking at oncology, you're trying to use machine learning to help the world in terms of alleviating suffering. If you look at natural language processing, you're focused on the outcomes of improving practical things like machine translation. But, you know, human-level intelligence is a thing that our civilization has dreamed about creating, superhuman-level intelligence. Do you think about this? Do you think it's at all within our reach?

• 1:03:37Speaker 01

  So as you said yourself earlier, talking about, you know, how do you perceive, you know, our communications with each other, that, you know, we're matching keywords and certain behaviors and so on. So at the end, whenever one assesses, let's say, relations with another person, you have separate kind of measurements and outcomes inside your head that determine, you know, what is the status of the relation. So one way, this is this classical dilemma, what is the intelligence? Is it the fact that now we are going to do the same way as human is doing, when we don't even understand what the human is doing? Or we now have an ability to deliver these outcomes, but not in one area, not in NLP, and not just to translate or just to answer questions, but across many, many areas, that

• 1:04:22Speaker 01

  we can achieve the functionalities that humans can achieve with their ability to learn and do other things. I think this is, and this, we can actually measure how far we are. And that's what makes me excited, that we, you know, in my lifetime, at least so far, what we've seen is like tremendous progress across with these different functionalities. And I think it will be really exciting to see where we will be. And again, one way to think about it is there are machines which are improving their functionality. Another one is to think about us with our brains, which are imperfect.

• 1:05:03Speaker 01

  How they can be accelerated by this technology as it becomes stronger and stronger. And coming back to another book that I love, Flowers for Algernon. Have you read this book?

• 1:05:19Lex Fridman?

  Yes.

• 1:05:19Speaker 01

  So there is this point that then the patient gets this miracle cure, which changes his brain. And all of a sudden, they see life in a different way and can do certain things better, but certain things much worse.

• 1:05:33Speaker 01

  So you can imagine this kind of computer augmented cognition, where it can bring you that now, in the same way as, you know, the cars enable us to get to places where we've never been before, can we think differently? Can we think faster? So, and we already see a lot of it happening in how it impacts us. But I think we have a long way to go there.

• 1:05:59Lex Fridman?

  So that's sort of artificial intelligence and technology affecting our, augmenting our intelligence as humans. Yesterday, a company called Neuralink announced, they did this whole demonstration. I don't know if you saw it. It's, they demonstrated brain, computer, brain machine interface, where there's like a sewing machine for the brain. Do you, you know, a lot of that is quite out there in terms of things that some people would say are impossible, but they're dreamers and want to engineer systems like that. Do you see, based on what you just said, a hope for that more direct interaction with the brain?

• 1:06:42Speaker 01

  I think there are different ways. One is a direct interaction with the brain. And again, there are lots of companies that work in this space. And I think there will be a lot of developments. But I'm just thinking that many times we are not aware of our feelings, of motivation, what drives us. Like, let me give you a trivial example, our attention. There are a lot of studies that demonstrate that it takes a while to a person to understand that they are not attentive anymore. And we know that there are people who really have strong capacity to hold attention. There are another end of the spectrum, people with ADD and other issues, that they have problem to regulate their attention. Imagine to yourself that you have like a cognitive aid that just alerts you based on your gaze, that your attention is now not on what you are doing.

• 1:07:26Speaker 01

  And instead of writing a paper, you're now dreaming of what you're gonna do in the evening. So even this kind of simple measurement things, how they can change us. And I see it even in the simple ways with myself. I have my zone app that I got in MIT gym. It kind of records, you know, how much did you run? And you have some points and you could get some status, whatever. Like, I said, what is this ridiculous thing? Who would ever care about some status in some app? Guess what? So to maintain the status, you have to do certain number of points every month. And not only that, I do it every single month for the last eighteen months. It went to the point that I was running, that I was injured.

• 1:08:11Speaker 01

  And when I could run again, I, in two days, I did like some humongous amount of running just to complete the points. It was like really not safe. It's like, I'm not gonna lose my status because I want to get there. So you can already see that this direct measurement and the feedback is, you know, we're looking at video games and see why, you know, the addiction aspect of it. But you can imagine that the same idea can be expanded to many other areas of our life when we really can get feedback. And imagine in your case, in relations, when we are doing keyword matching, imagine that the person who is generating the keywords, that person gets direct feedback before the

• 1:08:55Speaker 01

  whole thing explodes, that maybe at this happy point, we are going in the wrong direction. Maybe it will be really a behavior modifying moment.

• 1:09:05Lex Fridman?

  So, yeah, it's a relationship management too. So, yeah, that's a fascinating whole area of psychology, actually, as well, of seeing how our behavior has changed with, basically, all human relations now have other non-human entities helping us out. So you've, you teach a large, a huge machine learning course here at MIT.

• 1:09:31Lex Fridman?

  I could ask you a million questions, but you've seen a lot of students. What ideas do students struggle with the most as they first enter this world of machine learning?

• 1:09:42Speaker 01

  Actually, this year was the first time I started teaching a small machine learning class. And it came as a result of what I saw in my big machine learning class that Tommy Yackel and I built maybe six years ago. What we've seen that as this area become more and more popular, more and more people at MIT want to take this class. And while we designed it for computer science majors, there were a lot of people who really are interested to learn it. But unfortunately, their background was not enabling them to do well in the class. And many of them associated machine learning with the word struggle and failure, primarily for non-majors.

• 1:10:23Speaker 01

  And that's why we actually started a new class, which we call machine learning from algorithms to modeling, which emphasizes more the modeling aspects of it and focuses on, it has majors and non-majors. So we kind of try to extract the relevant parts and make it more accessible. Because the fact that we're teaching 20 classifiers in standard machine learning classes is really a big question we really needed. But it was interesting to see this from first generation of students, you know, when they came back from their internships and from their jobs, what different and exciting things they can do that I would never think that you can even apply machine learning to.

• 1:11:08Speaker 01

  Some of them are like matching, you know, their relations and other things, like variety of different applications.

• 1:11:12Lex Fridman?

  Everything is amenable to machine learning. You know, that actually brings up an interesting point of computer science in general. It almost seems, maybe I'm crazy, but it almost seems like everybody needs to learn how to program these days. If you're 20 years old or if you're starting school, even if you're an English major, it seems, it seems like programming unlocks so much possibility in this world. So when you're interacting with those non-majors, is there skills that they were simply?

• 1:11:45Lex Fridman?

  Lacking at the time that you wish they had and that they learned in high school and so on, like how will it, how should education change in this computer, computerized world that we live in?

• 1:11:58Speaker 01

  See, because they knew that there is a Python component in the class, you know, their Python skills were okay and the class is not really heavy on programming. They primarily kind of add parts to the programs. I think it was more of the mathematical barriers and the class against with the design on the majors was using the notation like big O for complexity and others. People who come from different backgrounds just don't have it in the lexical. It's not necessarily very challenging notion, but they were just not aware. So I think that, you know, kind of linear algebra and probability, the basics, the calculus, multivariate calculus are things that can help.

• 1:12:37Lex Fridman?

  What advice would you give to students interested in machine learning? Interested, you've talked about detecting curing cancer, drug design. If they want to get into that field, what, what should they do?

• 1:12:53Lex Fridman?

  Get into it and succeed as researchers and entrepreneurs?

• 1:13:00Speaker 01

  The first good piece of news is that right now there are lots of resources that, you know, are created at different levels and you can find online on your school classes, which are more mathematical, more applied and so on. So you can find a kind of preacher which preaches your own language where you can enter the field and you can make many different types of contribution depending of, you know, what is your strengths. And the second point, I think it's really important to find some area which you, for which you really care about and it can motivate your learning and it can be for somebody curing cancer or doing self-driving cars or whatever, but to find an area where, you

• 1:13:45Speaker 01

  know, there is data where you believe there are strong patterns and we should be doing it and we're still not doing it, or you can do it better and just start there and see where it can bring you.

• 1:13:57Lex Fridman?

  So you've, you've been very successful in many directions in life, but you also mentioned Flowers of Argon.

• 1:14:08Lex Fridman?

  And I think I read or listened to you mention somewhere that researchers often get lost in the details of their work. This is per our original discussion with Kant and so on. And don't look at the bigger picture, bigger questions of meaning and so on. So let me ask you the impossible question of what's the meaning of this thing? Of life, of your life, of research? Why do you think we descend and of great apes are here on this spinning ball?

• 1:14:43Speaker 01

  You know, I don't think that I have really a global answer. You know, maybe that's why I didn't go to humanities. I didn't take humanities classes in my undergrad.

• 1:14:56Speaker 01

  But the way I'm thinking about it, that each one of us inside of them have their own set of, you know, things that we believe are important. And it just happens that we are busy with achieving various goals, busy listening to others and to kind of try to conform and to be part of the crowd. That we don't listen to that part. And, you know, we all should find some time to understand what is our own individual missions. And we may have very different missions. And to make sure that while we are running 10,000 things, we are not, you know, missing out and we're putting all the resources

• 1:15:41Speaker 01

  to satisfy our own mission. And if I look over my time, when I was younger, most of these missions, you know, I was primarily driven by the external stimulus, you know, to achieve this or to be that. And now, a lot of what I do is driven by really thinking, what is important for me to achieve independently of the external recognition? And, you know, I don't mind to be viewed in certain ways. The most important thing for me is to be true to myself, to what I think is right.

• 1:16:24Lex Fridman?

  How long did it take? How hard was it to find the you that you have to be true to?

• 1:16:31Speaker 01

  So it takes time and even now, sometimes, you know, the vanity and the triviality can take, you know.

• 1:16:38Lex Fridman?

  At MIT.

• 1:16:38Speaker 01

  Yeah, it can everywhere. You know, it's just the vanity at MIT is different, the vanity in different places, but we all have our piece of vanity. But I think actually, for me, the many times, the place to get back to it is, you know, when I'm alone and also when I read. And I think by selecting the right books, you can get the right questions and learn from what you read. So, but again, it's not perfect. Like vanity sometimes dominates.

• 1:17:19Lex Fridman?

  Well, that's a beautiful way to end. Thank you so much for talking today.

• 1:17:23Speaker 01

  Thank you.

• 1:17:24Lex Fridman?

  That was fun.

• 1:17:24Speaker 01

  Well, it was fun.