Van Hans commited on
Update README.md
Browse files
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 |
-
*
|
| 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 |
|