Відео

Two take aways from this is that humans seem to have a very good understanding of the game of chess and are able to competitively handcraft evaluation functions that play as good as reinforcement learning engines. Second, is that two CNN using Montecarlo could evolve into completely different solutions using the same exact implementation 😮

Kotlin Notebook pls.

Roman, nice to see you using vector db as well, greetings from Canada

Nice talk, but in 2024, Stockfish is still better than alpha zero. Why?

Very well presented and great content! I struggle with understanding some accents and maintaining focus with many presenters, especially if they are not great communicators but Dr. Grebennikov is very articulate and easy to follow. Thank you!

Favourite talk of the conference!

Very helpful content, thanks for sharing.

It's really annoying when you desperately need help and chatbots are just redirecting you over and over,. They don't understand context so companies using these are definitely a turn off.

This was comprehensible, quite insightful too, thanks for sharing.

I play and I do not think, just repeat the same things wasting my time while waiting for the bullshiter since 2016

Great talk. A reasonable approach.

You made a Awesome video but nobody actually cares about ML in Kotlin . Because most of the wanted to learn ML chooses Python over ML

tHANK YOU, but I disagree that rook usage

the best investigation yielded approx. 10^42 positions and that is what counts.not the rough estimate of 10^120 possible games.

This is a very very nice talk, thank you!

awesome!

He sounds like he has no idea what he is talking about lol. Just the speech issue I think. Sorry for hate.

Just started learning chess and I know only a little about computer science/programming but this was wonderful to gain a better understanding of what chess engines are actually doing under the hood when I use them and also a better understanding of their limitations. I've noticed many people talk about people over-relying on engines so I figured it would be a good use of my time to gain a deeper understanding of what a chess engine even is if I'm going to be using them regularly. Also, it's just interesting and fun to learn! Thanks for the amazing lecture. :)

about the stockfish evaluation function, is it completely prewritten or are there some (handwritten) parameters that can be optimised through learning? (

I wanna see stockfish pull a Jerome opening now

Fantastic talk

There is one point, usually never mentioned. I will try to explain that (rather valid question) below, hoping, someone else will explain, why this is not a concern: Neural networks (deep or otherwise) act as function estimators. Here, it is the value function F(position) -> Value. As was pointed out early in the talk, this must be an approximation, because it would be cheating the universe if it managed to be exact in the presence of those high numbers of possible positions. (Store more information than number of atoms in the universe). So, an assumption is being made (and that is what is usually not elaborated): Positions, never seen before by the network still yield a value and the means of doing that is some form of interpolation. But for this to work, you assume a smooth value function (how ever high dimensional it is), you assume: V(P+Delta) = Value + Delta` for small enough deltas. So for this to work, the value function for chess has to be smooth-ish. But where did anyone ever prove, that this is the case? Here a simple example of the difference I try to point out: f1: Float -> Float f1 x = x * x If you sample F1 at some points, you can interpolate (with some errors) values between the samples: So, you train the network for, say: x in [1,3,5,7,...]. And when the network is trained and applied to values in [2,4,6], you get some roughly useful value (hopefully). Why? Because the function the network approximates is smooth. Here another function, not smooth: f2: Float -> Float f2 x = random x Training a network at the x in [1,3,5,7] cases does not yield a network which gives good estimators for the even x values. Why? Because that function is not smooth (unless you got lucky with your random numbers). So, which of the above F1, F2 is more akin to a chess value function V(position) -> Value? Who has shown, that chess is F1-ish?

can we get the code?

Wow just 4 minutes in and this is an excellent explanation. Just knowing whether or not stockfish had these "handcrafted" elements is so important to understanding how it works.

attending such a lecture for me is a dream , I can't believe that most of them don't play chess !!

Can someone give me some good reference material or guides for Time Series Analysis using Deep Learning?

Please what is the song at the beginning of the video! I've heard it before and now I want to listen to it! Thankyou!

Without analysing as a chess engine i can see it's actually better for black. Count 9 pieces around the king, both queens are at the 5th rank of the king so they are not included, but black has a rook while no rook is near the white king and the pawn structure has 1 shape out for them too, agains't 3 move on black and good defense around them with both pawn and major pieces. Black has 1 pawn on the 5th rank in font of this weak king also, while it's 1 pawn for H rank & G & E for white.

Stockfish 15 NNUE Plays ? The A.R.B Chess System ua-cam.com/video/NKK1WbinfNk/v-deo.html Stockfish 15 NNUE Plays The (A.R.B.C.S) - Kings & Pawns Game - A.R.B :) ua-cam.com/video/aFNvSLIzdDU/v-deo.html

Great presentation. I deal with a lot of time series using deep learning. This lecture gave me some ideas to test.

I liked his take on GPT ... 1000% accurate and respectable answer ...

thank you for mentioning generative autoencoders

It's because of content like this that I'll never get bored of trying to solve complex problems, really insightful and thought provoking 💫

10:45 as someone who is actually making a chess engine: Haha no.

Great talk on NLG! Simple, comprehensive and to the point. Thank you for doing this.

Awesome - excellent treatment - use-case by use-case

I don't understand why do you need the value function, if you have probabilities over possible moves, you will always during deployment select the argmax of the probability vectors... Is it for victory/defeat flags or something like that? Also, after each iteration of the MCTS, is the network trained until convergence or do you go over the self-played game only once?

Thank you for uploading this. It is very informative.

wow this is just amazing

I hate chatbots, I miss the good ole days when you could simply press 0 and talk to a human who could fix your problems easy peasy

Intel Core i7 11700K Motherboard Asus Z590 32GB RAM DDR4 1TB SSD GTX 1060 3GB DDR5 Hi this is my computer, and I use SF14, plus I have a 100 gb chess moves, but in a way I didn't get 100% of it. Can you help me? Ty

EXCELLENT TEACHING. I am a university teacher myself in the past!

Great talk!

Interesting talk. I do MehOps nowadays... I don't bloody cares about my stupid management..

Lot of preparation with Tensorflow to create a project, but it's the real deal. I hope some day I find the time to dig into this.

Mr Henkelmann j(DIVISIO) has supplied us with an excellent and informative video here. Thanks buddy I hope you make more, and good luck with your work there! It is such a good video because it's clear and brief and full of practical info I did not find elsewhere.

This is still by far the best lecture I've seen on the topic so far

This is very interesting... just finished the game. The accent is very strong though, and I'm kind of struggling to understand the speaker. Only worth watching for actual coders I think.

They should show the slide fullscreen so we don't have to zoom our eyes. We don't need the footage of the presenter speaking.

Very interesting contribution! However, the windows executable files, that are linked on the Github site, are down (404 error). Could you check that?