Changes

the preferred target platforms are [[Nvidia]] [[GPU|GPU’sGPUs]] supporting [https://en.wikipedia.org/wiki/CUDA CUDA] and cuDNN [https://en.wikipedia.org/wiki/CuDNN CuDNN] libraries <ref>[https://developer.nvidia.com/cudnn NVIDIA cuDNN | NVIDIA Developer]</ref>.[[Ankan Banerjee]] wrote the CuDNN backend code, also shared by [[Deus X]] and [[Allie]] <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=71822&start=48 Re: My failed attempt to change TCEC NN clone rules] by [[Adam Treat]], [[CCC]], September 19, 2019</ref>. None CUDA compliant GPUs ([[AMD]]) are supported through [https://en.wikipedia.org/wiki/OpenCL [OpenCL]], while much slower pure CPU binaries are possible using [https://en.wikipedia.org/wiki/Basic_Linear_Algebra_Subprograms BLAS], target systems with or without a [https://en.wikipedia.org/wiki/Video_card graphics card] (GPU) are [[Linux]], [[Mac OS]] and [[Windows]] computers, or BLAS only the [[Raspberry Pi]].

Lc0's color agnostic board is represented by five [[Bitboards|bitboards]] (own pieces, opponent pieces, orthogonal sliding pieces, diagonal sliding pieces, and pawns including [[En passant|en passant]] target information coded as pawns on rank 1 and 8), two king squares, [[Castling Rights|castling rights]], and a flag whether the board is [[Color Flipping|color flipped]].While the structure is suitable as input for the neural network, getting Getting individual pieces piece bitboards requires some [[General Setwise Operations|setwise operations]] such as [[General Setwise Operations#Intersection|intersection]] and [[General Setwise Operations#RelativeComplement|set theoretic difference]] <ref>[https://github.com/LeelaChessZero/lc0/blob/master/src/chess/board.h lc0/board.h at master · LeelaChessZero/lc0 · GitHub]</ref>.

While [[AlphaGo]] used two disjoint networks for policy and value, [[AlphaZero]] as well as Leela Chess Zero, share a common "body" connected to disjoint policy and value "heads". The “body” consists of spatial 8x8 input planes, followed by convolutional layers with using B [[Neural Networks#Residual|residual]] blocks times 3x3xF with F filtersof kernel size 3x3, stride 1. BxF specifies the So far, model and size sizes FxB of the CNN (64x6, 128x10, 192x15, and 256x20 were used).  Concerning [[Nodes per Second|nodes per second]] of the MCTS, smaller models are faster to calculate than larger models. They are faster to train and one may will earlier recognize progress, but they will also saturate earlier so that at some point more training will no longer improve the engine. Larger and deeper network models will improve the receptivity, the amount of knowledge and pattern to extract from the training samples, with potential for a [[Playing Strength|stronger]] engine. As a further improvement, Leele Chess Zero applies the ''Squeeze and Excite'' (SE) extension to the residual block architecture <ref>[https://github.com/LeelaChessZero/lc0/wiki/Technical-Explanation-of-Leela-Chess-Zero Technical Explanation of Leela Chess Zero · LeelaChessZero/lc0 Wiki · GitHub]</ref> <ref>[https://towardsdatascience.com/squeeze-and-excitation-networks-9ef5e71eacd7 Squeeze-and-Excitation Networks – Towards Data Science] by [http://plpp.de/ Paul-Louis Pröve], October 17, 2017</ref>.The body is fully connected to both the policy "head" for the move probability distribution, and the value "head" for the evaluation score aka [[Pawn Advantage, Win Percentage, and Elo|winning probability]] of the the the current position and up to seven predecessor positions on the input planes.

Like in [[AlphaZero]], the '''Zero''' suffix implies no other initial knowledge than the rules of the game, to build a superhuman player, starting with truly random self-play games to apply [[Reinforcement Learning|reinforcement learning]] based on the outcome of that games.However, there are derived approaches, such as [[Albert Silver|Albert Silver's]] [[Deus X]], trying to take a short-cut by initially using [[Supervised Learning|supervised learning]] techniques, such as feeding in high quality games played by other strong chess playing entities, or huge records of positions with a given preferred move.

The distributed training is realized with an sophisticated [https://en.wikipedia.org/wiki/Client%E2%80%93server_model client-server model]. The client, written entirely in the [[Go (Programming Language)|Go programming language]], incorporates Lc0 to produce self-play games.Controlled by the server, the client may download the latest network, will start self-playing, and uploading games to the server, who on the other hand will regularly produce and distribute new neural network weights after a certain amount of games available from contributors. The training software consists of [[Python]] code, the pipeline requires [https://en.wikipedia.org/wiki/NumPy NumPy] and [https://en.wikipedia.org/wiki/TensorFlow TensorFlow] running on [[Linux]] <ref>[https://github.com/LeelaChessZero/lczero-training GitHub - LeelaChessZero/lczero-training: For code etc relating to the network training process.]</ref>.

* [http://blog.lczero.org/2018/11/lc0-v0190-rc1-has-been-released.html LCZero blog: Lc0 v0.19.0-rc1 (UPD: rc2) has been released] by [[Alexander Lyashuk|crem]], [[Leela Chess Zero|LCZero blog]], November 9, 2018* [http://blog.lczero.org/2018/11/lc0-v0190-has-been-released.html LCZero blog: Lc0 c0 v0.19.0 has been released] by [[Alexander Lyashuk|crem]], [[Leela Chess Zero|LCZero blog]], November 9, 2018

* [[:Category:Marc RibotWeather Report|Marc Ribot'sWeather Report]] Ceramic Dog - Lies My Body Told Me [https://en.wikipedia.org/wiki/Live_in_Tokyo_(Live on Weather_Report_album) Vertical Invader / T.H. / Dr. Honoris Causa], album [https://en.wikipedia.org/wiki/KEXP-FM KEXPI_Sing_the_Body_Electric_(album) I Sing the Body Electric], July 20, 2016(1972), [https://en.wikipedia.org/wiki/YouTube YouTube] Video : {{#evu:https://www.youtube.com/watch?v=YohWv7kIp5oTTJwf4cCUwI|alignment=left|valignment=top}}

[[Category:Marc RibotGPU]][[Category:NN]][[Category:PC]][[Category:Windows]][[Category:Linux]][[Category:Mac]]