.png){kind=icon}
返回
Optimize TSK Fuzzy Systems for Classification Problems: Minibatch Gradient Descent With Uniform Regularization and Batch Normalization
.png){kind=icon}
OA
AI
DOI：10.1109/TFUZZ.2020.2967282.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Takagi-Sugeno-Kang (TSK) fuzzy systems are flexible and interpretable machine learning models; however, they may not be easily optimized when the data size is large, and/or the data dimensionality is high. This article proposes a minibatch gradient descent (MBGD) based algorithm to efficiently and effectively train TSK fuzzy classifiers. It integrates two novel techniques: First, uniform regularization (UR), which forces the rules to have similar average contributions to the output, and hence to increase the generalization performance of the TSK classifier; and, second, batch normalization (BN), which extends BN from deep neural networks to TSK fuzzy classifiers to expedite the convergence and improve the generalization performance. Experiments on 12 UCI datasets from various application domains, with varying size and dimensionality, demonstrated that UR and BN are effective individually, and integrating them can further improve the classification performance.
Keyword:
Training
Fuzzy systems
Neural networks
Convergence
Optimization
Evolutionary computation
Standards
Batch normalization (BN)
minibatch gradient descent
Takagi– Sugeno– Kang (TSK) fuzzy classifier
uniform regularization (UR)
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
11.9
论文数:
5.0K
被引数:
2.9W
机构
暂无机构信息
引用论文
.png){kind=icon}
分享收藏
查看更多内容