LcZero - CEDR Rating=3683 vBT4: Big transformer 4. New network architecture which builds off of BT3 by adding two types of auxiliary heads, future heads and categorical value heads. The categorical value heads predict a distribution over values of q rather than a WDL outcome distribution, and the future heads predict the moves that will be played over the next two plies. The hope is that these heads will give additional information to the net to improve training speed. We've also fixed half-precision training, so this model will be larger. BT4 training started in mid-October and is expected to take a few months. It has 15 layers with 1024 embedding size, 32 heads per layer, and 1536 emb size, for roughly a doubling in size over BT3. Individual statistics: Lc0 0.30.0 Stockfish 16 5/13 -3 13 Games Booot 7.2 6/10 +2 10 Games Critter 1.6a 8/9 +7 9 Games Dragon 3.2 4/8 +0 8 Games Stockfish 20230729 3.5/8 -1 8 Games ShashChess 33.2 3.5/8 -1 8 Games Fisherov chess monk 1.2 3/
Can someone explain to non experts just what is a NNUE engine, & how do you use them?
ReplyDeleteOk, there will be such a short tutorial soon
DeleteSoon?
ReplyDeleteNNUE uses a database from machine learning (the NN stands for neural network= the machine equivalent to a human brain)to update the program's move weights so it can use "memories" of previous played games to navigate through playing games instead of hard computations. The UE means that in order to make the program stronger (or smarter) they can update the database and give the program more or better "experience" playing chess. But this takes a significant amount of time. they've found an efficient way to do this.
ReplyDelete