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

“I understand it's like that. I understand volt. What define? What it means, a new predicate. Like a guy who understands music can say this word which he described when he listened to music. He understand music. He used not too many different, you can do like prop. You can make collection, what he talking about music, about this, about that. It's not too many different situations he described.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“So the story is formal story, mathematical story, is that you can use any function you want as a predicate. But some of them are good, some of them are not, because some of them reduce a lot of functions. Admissible setter. Some of them”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“and run like hosen and move slake horse. It is general predicate. That this applied to doc. But for doc, you can say play chess like that.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Roughly speaking, how many functions in this set? So you're decreasing, decreasing, and it makes easy for you to find function you're looking for. But the most important part. to create good admissible set of functions, and it probably there are many ways. But The good predicated such that can do that. For this duck, you should know a little bit about duck because.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“No, but If you reduce very well the VC dimension of the function of admissible set of function is small and you need not too much training data to do well.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Buy as much as possible. Good predicate which does this. Then I should choose next predicate which decrease as much as possible. So set of good predicate. It is such that they decrease. Amount of admissible”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“It is just small or big. I know exactly then when I introducing Some predicate I decrease set of functions. But my goal to degree set of function much.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Invariance say it is great to have people describe music we should learn from that. Something on this level, but so why Vladimir Prob who was just theoretical who studied theoretical literature, he found that.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“But what I am hope that there is a standard predicate like prop show. What I want to find for digit recognition. If we start, it is completely new area. What is intelligence about on the level starting from Plato's idea? What is world of ideas? And I believe that it's not too many. But, you know, it is amusing that mathematicians doing something in neural network in general function, but people from literature, from art, they use this all the time.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You should agree that it is much better to have a set of functions. And they say this set of functions should be admissible. It must keep this invariant, this invariant, and that invariant. You know that as soon as you incorporate new invariants, set of functions, because smaller and smaller and smaller.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Small set of functions. But it is fine, it is fine. I don't want to discuss the small or big advantage. So you have some set of functions. So now when you're trying to create architecture. You would like to create admissible set of functions. All your tricks to use, not all functions, but some subset of this set of functions. When you're introducing convolutional net, it is way to make this subset useful for you. But from my point of view, convolutional, it is something you want to keep some invariants, say translation invariants. But now, if you understand this, Cannot explain on the level of ideas what neural network does.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Its pace with infinite number of coordinates function for expansion something like that. So it's much richer. And when I'm talking about closed form solution, talking about this set of function, not piecewise linear set, which is particularly It is a small part”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You understand, but let's talk. Not on emotional level, but on a mathematical level. You have set of piecewise linear functions. It is all possible neural networks. Just piecewise linear functions. There's many, many pieces.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“That is a risk, not too many predicates. And that is a big story because Jan did it 25 years ago and nothing so clear was added to deep network. And then I don't understand why we should talk about deep network instead of talking about piecewise linear functions, which keeps predicate.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“In my talk, I gave example for diabetes. When we achieve some percent, so then we are looking from Some sort of predicate, which I formulate does not. Invariant So if it doesn't keep, I retrain my data, I select only function which keeps this invariant. And when I did it, I improved my performance. I can look for this predicate. I know technically how to do that. And you can, of course, do it using machine. But I'm not sure that we will construct the smartest predicate.”
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 that machine can do because According to theory about weak convergence. Any function from Hilbert space can be predicated. So you have infinite number of predicate and before you don't know which predicate is good and which, but whatever And why people call it breakthrough that there is not too many Which cover Most of the situation happened in the world”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“But my point is why I hope that it's possible to beat record. Using not 60,000, but say 100 times less, because instead you will give predicates. And you will select your decision not from wide set of functions, but from set of functions which keep this predicate. But predicate is not related just to digit recognition.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“The Russian fairy tale. But a Russian fairy tale is not so interesting. More interesting than people applied this to movies, to theater, to different things. And the same works. They are universal.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Yeah, but property, you can know independent on training data. And this guy, prop. So that there is formal property. 31 property”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“V convergence means any property. Convergence not point wise, but integral property of function. So the convergence means integral property of functions. When I talking about predicate, I would like to formulate which integral properties I would like to have for convergence. And if I will take one predicated function which I measure property. If I will use one predicate and say I will consider only function which gives me the same value as with this predicate by selecting set of functions From functions which is admissible in the sense that function which I'm looking for in this set of functions because I checking in training data it gives the same”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Convergence in functions. You have different convergence in functionals. You take any function, you take some function phi. Take inner product this function is f function. Zero function which you want to find. And that gives you some value. So you say that Set of functions converge. Inner product to this function if this value Inner product converges to value That is for one fee. But V converges requires that it converge for any function. It converges for any function of Hilbert space, then you will say that this is weak convergence. You can think that you take integral that is integral property of function For example, if you will take sine or cosine, it is coefficient of, say, Fourier expansion. So if it converges, For all coefficients of Fourier expansion, so under some condition it converged to function you're looking for.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“It's pretty large, but if you have one predicate. But according to, there is a strong and weak convergence. Strong convergence convergence and function. You're looking at the function from one function and you're looking on the another function and square difference. From them should be small. If you take difference in any points, make a square, make an integral, and it should be small. That is convergence in function. Suppose you have some function, any function. So I would say that some function converges to this function. if integral from square difference between them is”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I would like to have these functions. I have some examples. Can consider protruding of these examples. And I can measure level of symmetry for every digit. Then I can take from my training data and I will consider only functions Conditional probability, which I am looking for my decision rule. Digits will give me the same average as I absorb on training date. So actually, this is different level of description of what you want. You show not one digit. You show this predicate, show general property Of all digits which you have in mind. If you have in mind digits three, it gives you property of digit 3 and you select as admissible set of function, only function, which keeps this property. You will not consider other functions. So you're immediately looking for smaller subset of function.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Conver You would like to have a function. The function which say indicator function which indicate your Digit 5, for example.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“It is not necessarily for digital cognition. It helps. create invariant which will which you can use when you will have examples for digital recognition. You have regular problem of digital recognition. You have examples of the first class. Plus, you know that there exist concept of symmetry. And you apply when you're looking for decision rule, you will apply Concept of symmetry, of this level of symmetry which you estimate from me. So let's talk. Everything is Comes from weak conver”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“No, no, I'm talking about digit. I would like to concentrate on all, I would like to know, predicate for digit recognition.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“There is a D of symmetry, and you can this idea of symmetry make Like degree of symmetry. If degree of symmetry can be zero, no symmetry at all degree of symmetry, say more or less symmetrical. but you have one of this description asymmetry can be different. As I told horizontal, vertical, diagonal, and anti-symmetry is also concept of symmetry.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Right, but there is a degree of symmetry. If you play all this leader stuff to Do tangent distance, but whatever I described, you can have a degree of symmetry. And that is what describing reason of image. It is the same as you will describe this. Think about Digitest, it has anti-symmetry, Digit3 symmetric, more or less look for symmetry.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You're going to symmetries. There is a symmetry anti-symmetry say letter S. So it has vertical anti-symmetry. And it could be diagonal symmetry, vertical symmetry.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I don't know Because it's so complicated. It involves a lot of stuff which I never consider. But I know about digital recognition. And I know that For digit recognition. So Get records from small number of observations, you need predicate. But not special predicate for this problem. But universal predicates which understand vault of images.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“In reality, you can realize this projection with invariance because it is projection on specific examples which create specific features of specific objects.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Invariance is T. Your image I can say looking on my image it is more or less symmetric and I can give you a value of symmetry say level of symmetry using this function which I gave yesterday And you can describe Your image has these characteristics exactly in the way how musical critics describe music. So but this is invariant applied to specific data, to specific music, to something. I strongly believe in these plot ideas that there exists world of predicate and vault of reality in reality is somehow connected and you have to”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“No, no, no, it's not on this level. It should not describe two, three, four. It describes some construction which allow you to create invariants.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“You know that is exam When crit Music trying to describe music, they use predicate. Not too many predicate, but in different combination. But they have some special words for describing music. The same should be for images. But maybe there are critics who understand. Essence of what this image is about.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“This formal definition say something heavy on the left corner, not so heavy in the middle and so on. You describe in general concept of what you assume.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Inputs is x something which is input in reality. Say if you consider digit recognition, it pixel space. Input, but it is function which in pixel space. But it can be any function from pixel space. And you choose, and I believe that there are several functions, which is important for understanding of images. One of them is symmetry. It's not so simple construction, as I described with linearity, with all this stuff. Not there, I believe, I don't know how many is how well structurized is picture.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“In my definition, the simplest predicate is function. Function and you can use this function to make inner product that is predicated.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“I think that we have a lot of form of behavior, but I think that predicate is much less. Because even in these examples, That predicate can be One predicate can construct many different invariants depending on your data. They are applying to different data and they give different invariance, but pure ideas. Maybe not so much.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“ideas in way to constructing invariant is intelligence. But first of all, predicate if you know predicate and hopefully not too much predicate exists. For example, 31 predicate for human behavior is not a lot.”
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 different between you have different goals. So Your goal is to create something useful. And that is great. And you can see how much things was done. And I believe that it will be done even more. Yet self driving cars and also this business. It is great. And it was inspired by Turing vision. Understanding is very difficult. It more or less philosophical category, what means understand the world. I believe in him which starts from Plato that there exists vault of ideas. I believe that intelligence it is vault of ideas, but it is vault of pure ideas. And when you Combine with reality things, it creates, as in my case invariance, which is very specific. And that I believe the combination”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source
“Completely different story. Engineering is a limitation of human activity. You have to Device which behaves as human behavior. all the functions of Does not matter how you do it. But to understand what is intelligence Quite different problem. So I think, I believe, that it's somehow related to predicate we talk yesterday about. because Look at the Vladimir Just found 31 here. predicates. units. Can explain humor behavior, at least in Russian tales. Look at Russian tales and derive from that, and then people realize that it more widespread than in Russian tales. It is in TV, in movie serials, and so on and so on.”
2020-02-14 · Lex Fridman Podcast · Vladimir Vapnik: Predicates, Invariants, and the Essence of Intelligence · IDENTIFIED FROM THE TRANSCRIPT · source