Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System
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.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationKnowledge DistillationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Financial Series Forecasting: A New Fuzzy Inference System for Crisp Values and Interval-Valued Predictions
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
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 ForecastingMulti-Label Takagi-Sugeno-Kang Fuzzy System
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-ClASSIFICATIONA Deep Neuro-Fuzzy Network for Image Classification
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 ClassificationDistilling Deep Reinforcement Learning into Interpretable Fuzzy Rules: An Explainable AI Framework
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