paper-with-me

홈 › Papers

Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System

2020-10-10 · Xiangming Gu, Xiang Cheng

Deep neural networks (DNNs) demonstrate great success in classification tasks. However, they act as black boxes and we don't know how they make decisions in a particular classification task. To this end, we propose to distill the knowledge from a DNN into a fuzzy inference system (FIS), which is Takagi-Sugeno-Kang (TSK)-type in this paper. The model has the capability to express the knowledge acquired by a DNN based on fuzzy rules, thus explaining a particular decision much easier. Knowledge distillation (KD) is applied to create a TSK-type FIS that generalizes better than one directly from the training data, which is guaranteed through experiments in this paper. To further improve the performances, we modify the baseline method of KD and obtain good results.

📄 PDF Abstract BibTeX arXiv:2010.04974

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationKnowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Financial Series Forecasting: A New Fuzzy Inference System for Crisp Values and Interval-Valued Predictions

2024-07-31 · Computational Economics 2024 7 · Kaike Sa Teles Rocha Alves, Rosangela Ballini, Eduardo Pestana de Aguiar

Fuzzy inference systems emerged as a machine learning model that provides accurate and explainable results. Two fuzzy inference systems are reported in the literature, Mamdani and Takagi–Sugeno–Kang. Mamdani implements f…

A new Takagi–Sugeno–Kang model for time series forecasting

2024-07-01 · Engineering Applications of Artificial Intelligence 2024 7 · Kaike Sa Teles Rocha Alves, Caian Dutra de Jesus, Eduardo Pestana de Aguiar

A fuzzy inference system consists of a machine learning concept that combines accuracy and interpretability. They are divided into two main groups: Mamdani and Takagi–Sugeno-Kang. While Mamdani models favor interpretabil…

Time SeriesTime Series Forecasting

Multi-Label Takagi-Sugeno-Kang Fuzzy System

2023-09-20 · Qiongdan Lou, Zhaohong Deng, Zhiyong Xiao, Kup-Sze Choi 외

Multi-label classification can effectively identify the relevant labels of an instance from a given set of labels. However,the modeling of the relationship between the features and the labels is critical to the classific…

ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

A Deep Neuro-Fuzzy Network for Image Classification

2019-12-22 · Omolbanin Yazdanbakhsh, Scott Dick

The combination of neural network and fuzzy systems into neuro-fuzzy systems integrates fuzzy reasoning rules into the connectionist networks. However, the existing neuro-fuzzy systems are developed under shallow structu…

ClassificationGeneral Classificationimage-classificationImage Classification

Distilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework

2026-02-24 · Sanup S. Araballi, Simon Khan, Chilukuri K. Mohan arxiv

Deep Reinforcement Learning (DRL) agents achieve remarkable performance in continuous control but remain opaque, hindering deployment in safety-critical domains. Existing explainability methods either provide only local …

Reinforcement LearningContinuous Control