论文标题
将深层神经网络提炼成高大的sugeno-kang模糊推理系统
Distilling a Deep Neural Network into a Takagi-Sugeno-Kang Fuzzy Inference System
论文作者
论文摘要
深度神经网络（DNNS）在分类任务中表现出巨大的成功。但是，它们充当黑匣子，我们不知道他们如何在特定的分类任务中做出决定。为此，我们建议将知识从DNN提炼为模糊的推理系统（FIS），该系统是本文中的Takagi-Sugeno-Kang（TSK）型。该模型可以根据模糊规则表达DNN获得的知识，从而更容易解释特定的决定。知识蒸馏（KD）用于创建一个TSK型FI，该FI直接从训练数据中概括了，该FI可以通过本文中的实验来保证。为了进一步改善性能，我们修改了KD的基线方法并获得良好的结果。
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.
