A game method for improving the interpretability of convolution neural network

TL;DR

This paper proposes a novel game-based method to enhance the interpretability of convolutional neural networks by constructing logical networks and analyzing the relations between layers, demonstrated on benchmark and real-world data.

Contribution

It introduces a new game method for building logical networks from fully connected layers to improve CNN interpretability, addressing a key challenge in deep learning explainability.

Findings

Improved interpretability demonstrated on benchmark datasets.

Logical relations between input and output layers extracted successfully.

Enhanced understanding of CNN decision processes.

Abstract

Real artificial intelligence always has been focused on by many machine learning researchers, especially in the area of deep learning. However deep neural network is hard to be understood and explained, and sometimes, even metaphysics. The reason is, we believe that: the network is essentially a perceptual model. Therefore, we believe that in order to complete complex intelligent activities from simple perception, it is necessary to con-struct another interpretable logical network to form accurate and reasonable responses and explanations to external things. Researchers like Bolei Zhou and Quanshi Zhang have found many explanatory rules for deep feature extraction aimed at the feature extraction stage of convolution neural network. However, although researchers like Marco Gori have also made great efforts to improve the interpretability of the fully connected layers of the network, the problem is also very difficult. This paper firstly analyzes its reason. Then a method of constructing logical network based on the fully connected layers and extracting logical relation between input and output of the layers is proposed. The game process between perceptual learning and logical abstract cognitive learning is implemented to improve the interpretable performance of deep learning process and deep learning model. The benefits of our approach are illustrated on benchmark data sets and in real-world experiments.