Vision Transformers for Computer Go

TL;DR

This paper investigates the application of Vision Transformers in the game of Go, comparing their performance to Residual Networks across various metrics like accuracy, win rates, and efficiency.

Contribution

It provides a detailed analysis of Vision Transformers' effectiveness in Go, highlighting their potential advantages over traditional Residual Networks.

Findings

Transformers achieve competitive prediction accuracy.

Transformers show improved win rates in Go.

Transformers demonstrate favorable memory and speed performance.

Abstract

Motivated by the success of transformers in various fields, such as language understanding and image analysis, this investigation explores their application in the context of the game of Go. In particular, our study focuses on the analysis of the Transformer in Vision. Through a detailed analysis of numerous points such as prediction accuracy, win rates, memory, speed, size, or even learning rate, we have been able to highlight the substantial role that transformers can play in the game of Go. This study was carried out by comparing them to the usual Residual Networks.