Deep learning and computer chess (part 1)

• Main Author: Muhammad Riaz Bin Jamalullah
• Other Authors: He Ying
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science; Chess; Deep learning; Neural network evaluation
• Online Access: https://hdl.handle.net/10356/181178
• Institution: Nanyang Technological University

This paper focuses on two novel implementations of modern chess engines that use neural networks: Giraffe and DeepChess. Both models aim to evaluate chess positions without relying on handcrafted heuristics that are common in traditional chess engines. Giraffe consists of a three-layer feed-forward...