YouSaid · the spoken record

Vladimir Vapnik

lines on the record: 91
first: 2020-02-14
most recent: 2020-02-14
sittings or episodes: 1
sources: podcast

Every line below is reproduced as it was said and linked to the record it came from. Nothing here is summarised or generated. Directory · Search · Corrections

“The nose that he is just his fantasy, but you know, every week we have a guy who is just. Writer and also Suritsko literature. And Have here understand literature and human relationship, have he seen life? And I understood that I'm just small comparing to Is very smart guy in understanding lie. Know this predicate here, he knows big blocks of life. I am used every time when I listen to him. And he just talked about it. And I think that I was. Surprised Manag Big companies. Most of them are guys who study English language in English literature. Why? Because they understand life, they understand models, and among them maybe many talented critics. Just analyzing this. And this is big science, like Prop did blocks. Very smart.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Very interesting. Have in Russia, I don't know, the guy Strug Have a There are Type of people Common people and very smart people. They just started. These two branches of people will go in different direction very soon. So that's what they're thinking about.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I even have some examples. So I have a friend. Specialist in Russian poetry. She is professor of Russian poetry. He did not write. Poems, but she Know a lot of stuff. Make a book, several books in one of them is a collection of Russian poetry. images of Russian poetry. She collects all images of Russian poetry. And I ask you to do the following. You have NIPS digit recognition. and you get 100 digits or maybe less than 100. I don't remember, maybe 50 digits. Trive from poetical point of view describe every image which we see using only images of Russian poetry. And then you try to Call it Lord Niffusing Privileged Information. I call it privileged information. You have on two languages. One language is just image of digit. In another language poetic description of this image. This is privileged information.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You know, the most time it is not to make this collection, to understand what is the common, to think about that once again and again and again.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Not too much Not too much. It is pity that I will not be able to do something which I think. I have a feeling to do that. For example You'll be very happy. Work this, guys. Theoretician from music. Write this collection of description, how they describe music, how they use what predicate. And from art as well. Then take what is in common. Try to understand predicate, which is absolute for everything.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Is ill problems. When you go from a DS2 to the representation, it is easy way. But when you're trying to go back, you'll post problems. But nevertheless, I believe that when you're looking from that, even from art. you will be able to find predicate for digital recognition.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Interpretation They're trying to explain new music. What the youth is. They describe high level ideas of Plato's ideas behind this music.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You know, it is very interesting to read what critics writing about Bach, which words they're using. They're trying to describe predic And then Schopen. It is very different vocabulary, very different. And I think that. You will make a collection of that. The media from this you can describe predicate for digit recognition.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I think that maybe. I don't know Maybe this is Should blame for that because empirical risk minimization, all this stuff. And if you read now textbooks, they just about bound, about empirical risk minimization. They don't look in. For another problem like admissible set.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Level of symmetry will be Level of symmetry, anti symmetry, jogano, vertical. I even don't know how you can use in different direction idea of symmetry. It's very general. But it will be there. I think the people very sensitive to ideosimiti. But there are several Ideas like symmetry symmetry I would like to learn, but you cannot learn just thinking about that. You should do challenging. Why we were able to solve them. And then we will see. Very simple things, it's not easy to find. Even we're talking about this every time. I was surprised. I tried to understand. Is people describe in language? Strong convergence mechanism for learning. I don't know. But weak convergence was a dark story, a story like that when you will explain. You will use the convergence arcuate. It looks like it does like it.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I working, I think about the same problem for 50 years or more. And again and again and again. Trying to be honest, and that is very important not to be very enthusiastic. but concentrate on whatever was not able to achieve. And understand a way. Know, I understand that because I believe in mass, I believe that In Vignor's Adieu. But no, when I see that there are only two ways of convergence. And we're using both. That means that we must do as well as People McNaws, exactly in philosophy, what we know about predicate, how we understand life, can we describe as a predicate? I thought about that. That is more or less obvious level of symmetry. But next Have a feeling Something about structures I don't know how to formulate, how to measure and measure of structure and all this stuff. And guy who will Solves this challenge problem.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Let's talk what is philosophy. Philosophy means understanding of life. So, understanding of life, people like Plata, they understand on very high abstract level of life. So, in whatever are doing, it's just implementation of my understanding of life. But every new step. It is very difficult. For example Find this idea that we need. Convergence. Was not simple”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“It's like predicate. the admissible set of functions It comes together, everything. The first iteration of theory was done 50 years ago, I told Mr. So everything there. If you have data, in your set of function is... Have not big capacity So law of this dimension, you can do that, you can make structural risk minimization, control capacity. He was not able to make admissible set of function. Know when suddenly realized that we did not use another idea of convergence, which we can. Everything comes together.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You know, most of things I don't understand. reasoning in human It is for me too complicated For me, the most difficult part. Is Ask questions Good questions how it works, how people asking questions. Don't know this.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You suggesting that let us use this type of algorithm. When I started thinking, I first of all starting to understand what I want. What I want. And then I try to formalize. And when I do that, Think you have to solve this problem. Still more I did not see situation”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Absolutely. When you're doing the self-driving cars The great guy who will do this. It does not matter what. Theory behind that. Who has a better feeling have to apply. But by the way, It is the same story about predicates because you cannot create rule for situation is much more than you have rule for that. Maybe you can have more abstract rule than it will be less than the rule. It is the same story about a DS applied to specific cases.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You know I'm looking on bones which I gave bones. And when I'm looking for Are What is the most appropriate kernel for this bound would be? You know the Our businesses use radial basis function. But looking on the bone, I think that I start to understand that maybe we need to make corrections to radial basis function to be Work better for these bones, so I'm again trying to understand what type of kernel. approximation no no approximation best fit to this ball”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You know, in classical mathematics Gilbert Space, there are only two forms of convergence, strong and weak. You can use both That means that we did everything. So happened that when we use Hilbert space, which is a very rich space of continuous functions, Each has an integral square. So we can apply weak and strong convergence for learning and have closed form solution. So for computationally simple, for me it is sign that it is the right way. because you don't need any stick. You just do whatever you want. But no, the only what left is concept of what is predicated. But it is not statistics.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I think about myself, how stupid I was 50 years. I did not see weak convergence. I work on strong convergence. But now I think that most powerful is weak convergence because it makes admissible set of functions. And even in proverbs, when people try to understand recognition about drug law, looks like a dog and so on. They use weak convergence. People in language, they understand this. But when we're trying to create artificial intelligence, If you want them in a different way. Just consider strong convergence arguments.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You have law of large numbers. So for any function, expectation of function average of function converged expectation. But if you have set of functions for any function, it is true. But it should converge simultaneously for all set of functions. For learning, you need Uniform convergence. Just convergence is not enough. Because when you pick up one which gives minimum, You can pick up. One function which does not converge and it will give you the answer. For this function. So, you need uniform convergence to guarantee learning. So learning does not rely on trivial law of large numbers. It rely on universal. Of the convergence existing statistics for a long time. But It is interesting that”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Don't know about babies if you will do. From very small examples You will find principles Will buy the paper From what we're using now. And so it's called it's more or less clear. That means that you will use weak convergence, not just strong convergence.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“No, no, no letter language is much, much more complicated. It involves a lot of different stuff. It's not just understanding of very simple class of tasks. I would like to see lists of tasks with language involved.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“What their idea is to predicate what can be predicate. I still symmetry will play a role in real life images in any real life images, 2D images. Let's talk about 2D images. That's what we know. Neural network was created for two data images.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I don't know, I don't think in this direction. I just think in direction that this is a problem. Which, if we will. We will create Some abstract understanding of images. Maybe not all images. I would like to talk to guys who are doing in real images in Columbia University.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You know, let me refer to Einstein. Take the simplest problem as simple as possible, but not simpler. And this is challenge. It's simple problem. But it's simple by idea, but not simple to get it. When you will do this, Will find some predicate, which helps”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You have several functions. But the Then you will apply them to reality, to your data, and you will create in this way predicate, which is useful for your task. But predicate are not related specifically to your task, to this task. It is abstract functions, which being applying apply to”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“It is discovered of your understanding world, of your methodology of understanding Because you have several functions which you will apply to reality.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I hope no, it's still neat evaluation, some bounce. But idea is the following. If you trust that This average gives you something close to expectation, so you can talk about that, about this predicate. And that is basis of human intelligence”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“But that is another story. I don't touch it because I believe that this small example is not too small, say 60 per class, that law of large numbers works. I don't need uniform law. The story is that in statistics there are two laws, law of large numbers and uniform law of large numbers. So I want to be in situation where I use law of large numbers, but not uniform law of large numbers.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You know, even from the classical this theory. From structure risk minimization. You should organize function in the way that They will be useful for you And that is”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“But let's think about examples. You have huge set of functions and you have several examples. If you're just trying to take function which satisfies these examples, You still will overfit. Need decreases, you need admissible set of functions.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, you'll have a fitting. So, you should Decreased set of functions from which you're picking up one. So you should go somehow to admissible set of functions. And this, what about weak conversions? From another point of view, To make Admissible set of functions. You need just a dig, just function which you will take in inner product, which you will measure. property of your function. And that is how it works.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I think that it is, you know, my scheme is very simple. You have a huge set of functions. If you will apply, and you have not too many data. If you pick up function which describes this data, You will do not very well”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, but you should make a projection on reality. But understanding is it is abstract ideas. You have in your mind. Several abstract ideas which you can apply to reality.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“No no no no no it is it is Next stop of Wigner that mathematics understands something in reality. It is the same plotter line. Then it comes suddenly to Vladimir Propriet. Look, 31 ideas, 31 units, and describes everything.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“But it is the way how you should try to understand how attack ideas in the world. So from my point of view, It is very clear, but it is line. All the time people looking for that. Say Plato, then Hegel Whatever reasonable it exists, whatever existed is reasonable. I don't know what you have in mind reasonable.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“And I would say that I did not understand Plata. until recently and until I consider weak convergence and then predicate and then no, this is what plotted. You linger.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah. But I would like to make a remark. I start not from problem make a challenge problem I start with very general problem with plato So it comes from plata to digit recognition.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You know, I cannot think. Things which I don't understand. This I understand, but I'm sure that I don't understand everything there. And that is the exact case. With hand”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Immediately, you will understand this. As soon as you will make a record. Because it is not for free. As soon as you will create Several invariants which will help you Get the same That's the best neural net did using 100 and maybe more than 100 times less examples. You have to have something smart to do that.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“But it is not. It is maybe, I want some universal invariance which are good not only for digit recognition, for image understanding”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Because you should know reality. You should know life. This guy like... You know something and you try to put in invariant his understanding.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“So everything is very simple. When you have infinite number of predicates, You can choose The function you want. You have invariance and you can choose the function you want. You have to have a Not Invariance. Solve the problem So, and half from infinite number of function to select Finite And hopefully small number of functions. Is good enough. To extract small set of admissible functions. So they will be admissible for sure because every function just decreased set of function and leaving it admissible. But it will be small.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Lecon physics, find situation where you have contradiction for one of the protests. One of the predicates. Then include this predicate making invariance and solve again this problem now you don't have contradiction. But it is not. The best way, probably, I don't know, to looking for predicate.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Quite contradict Then remove this contradiction. But in my case, what means contradiction you find function which if you will use this function, you're not keeping convariable.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Grat students listening right now. I gave example. So find situation. predicate which you're suggesting. Don't create invariant Like in physics, fine situation where existing theory cannot explain it.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“No, I'm not against neural network. I am against admissible set of functions which create neural network. You did it by hand. You don't do it by invariance, by predicate, by reason.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You're using examples as well. John says that if you will use Functions. All possible predicate. You don't need training data. You just view. Have admissible set of functions which contain one function.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“No, no, no, I'm not talking about predicate. Understand that it involves symmetry, maybe structure, maybe something else. I cannot formulate. I just was able to find symmetries, degree of symmetries.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“But at least there is a unit. It's not too many units that can describe, but this guy probably gives another units. Exactly.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source