Knowledge Distillation of Convolutional Neural Networks through Feature Map Transformation using Decision Trees

arXiv:2403.06089v1 Announce Type: new
Abstract: The interpretation of reasoning by Deep Neural Networks (DNN) is still challenging due to their perceived black-box nature. Therefore, deploying DNNs in several real-world tasks is restricted by the lack of transparency of these models. We propose a distillation approach by extracting features from the final layer of the convolutional neural network (CNN) to address insights to its reasoning. The feature maps in the final layer of a CNN are transformed into a one-dimensional feature …

abstract arxiv box convolutional neural networks cs.cv decision decision trees distillation dnn eess.sp feature interpretation knowledge map nature networks neural networks reasoning tasks through transformation transparency trees type world