Van Hans commited on
Commit
8a41d1b
·
verified ·
1 Parent(s): 61f50df

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ The core of the network is a Deep Residual Network (ResNet), a structure well-su
13
  ## **Torso:**
14
  The network employs a robust torso composed of 20 Residual Blocks. Each block contains convolutional layers with skip connections, allowing for the effective learning of deep, hierarchical features and maintaining stable training.
15
 
16
- * ** #Feature Processing:#** The entire network processes data using a high number of channels, specifically 512 filters in its main convolutional layers.
17
 
18
  * **Input Representation:** The current board state and history are encoded into a multi-plane tensor with 128 input channels, which typically includes information about piece locations, the player to move, castling rights, and repetition history, a common input format for state-of-the-art chess AI.
19
 
 
13
  ## **Torso:**
14
  The network employs a robust torso composed of 20 Residual Blocks. Each block contains convolutional layers with skip connections, allowing for the effective learning of deep, hierarchical features and maintaining stable training.
15
 
16
+ * # ** Feature Processing:** # The entire network processes data using a high number of channels, specifically 512 filters in its main convolutional layers.
17
 
18
  * **Input Representation:** The current board state and history are encoded into a multi-plane tensor with 128 input channels, which typically includes information about piece locations, the player to move, castling rights, and repetition history, a common input format for state-of-the-art chess AI.
19