paper-with-me

홈 › Papers

Multi-Labelled Value Networks for Computer Go

2017-05-30 · Ti-Rong Wu, I-Chen Wu, Guan-Wun Chen, Ting-Han Wei, Tung-Yi Lai, Hung-Chun Wu, Li-Cheng Lan

This paper proposes a new approach to a novel value network architecture for the game Go, called a multi-labelled (ML) value network. In the ML value network, different values (win rates) are trained simultaneously for different settings of komi, a compensation given to balance the initiative of playing first. The ML value network has three advantages, (a) it outputs values for different komi, (b) it supports dynamic komi, and (c) it lowers the mean squared error (MSE). This paper also proposes a new dynamic komi method to improve game-playing strength. This paper also performs experiments to demonstrate the merits of the architecture. First, the MSE of the ML value network is generally lower than the value network alone. Second, the program based on the ML value network wins by a rate of 67.6% against the program based on the value network alone. Third, the program with the proposed dynamic komi method significantly improves the playing strength over the baseline that does not use dynamic komi, especially for handicap games. To our knowledge, up to date, no handicap games have been played openly by programs using value networks. This paper provides these programs with a useful approach to playing handicap games.

📄 PDF Abstract BibTeX arXiv:1705.10701

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Model-free inference of unseen attractors: Reconstructing phase space features from a single noisy trajectory using reservoir computing

2021-08-06 · André Röhm, Daniel J. Gauthier, Ingo Fischer

Reservoir computers are powerful tools for chaotic time series prediction. They can be trained to approximate phase space flows and can thus both predict future values to a high accuracy, as well as reconstruct the gener…

Time SeriesTime Series AnalysisTime Series Prediction

Anomaly Detection in Automated Fibre Placement: Learning with Data Limitations

2023-07-15 · Assef Ghamisi, Todd Charter, Li Ji, Maxime Rivard 외

Conventional defect detection systems in Automated Fibre Placement (AFP) typically rely on end-to-end supervised learning, necessitating a substantial number of labelled defective samples for effective training. However,…

Anomaly DetectionBinary ClassificationDefect Detection

Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Models

2023-09-26 · Eman Ali, Muhammad Haris Khan

Recent advances in large-scale vision-language models have achieved impressive performance in various zero-shot image classification tasks. While prior studies have demonstrated significant improvements by introducing fe…

image-classificationImage ClassificationKnowledge DistillationPseudo Label+1

GANsfer Learning: Combining labelled and unlabelled data for GAN based data augmentation

2018-11-26 · Christopher Bowles, Roger Gunn, Alexander Hammers, Daniel Rueckert

Medical imaging is a domain which suffers from a paucity of manually annotated data for the training of learning algorithms. Manually delineating pathological regions at a pixel level is a time consuming process, especia…

Data AugmentationSegmentation

Applications and Effect Evaluation of Generative Adversarial Networks in Semi-Supervised Learning

2025-05-26 · Jiyu Hu, Haijiang Zeng, Zhen Tian

In recent years, image classification, as a core task in computer vision, relies on high-quality labelled data, which restricts the wide application of deep learning models in practical scenarios. To alleviate the proble…

Classificationimage-classificationImage ClassificationImage Generation+1