From 220a4b79e4b6d742a9ca7c278a1962b870500fbc Mon Sep 17 00:00:00 2001 From: tslil Date: Thu, 10 Sep 2026 14:12:41 +0100 Subject: credit Mitchell Riley: we can drop 65 parameters for about the same strength; also train for longer The idea is that the current model is M_theta(board, ply) = "score for player 0", but we can instead create a different model M'_theta(board) = "score for player 0 assuming that it's player 0's move" and for a certain pair of functions sigma, normalise, recover M_theta(board, ply) = sigma(ply) M'_theta(normalise(board, ply)). This pair of functions is sigma(ply) = +/- 1 (parity), and normalise being a conditional interchange of pieces on the board depending on the parity of the ply. The only things stopping this from being completely straightforward is that nn_train.py evaluates M'_theta itself so we need to pass sigma(ply) to the training loop. 6x6 is still untrained. --- include/weights_5.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/weights_5.h') diff --git a/include/weights_5.h b/include/weights_5.h index 16a9465..8ad9d1b 100644 --- a/include/weights_5.h +++ b/include/weights_5.h @@ -18,7 +18,7 @@ #ifndef WEIGHTS_5_H #define WEIGHTS_5_H -#define FIVE_INP_NUM 3 + 5 * 5 +#define FIVE_INP_NUM (2 + 5 * 5) #define FIVE_DENSE_NUM 64 // this does some kind of magic vectorisation -- cgit v1.3.1