A game method for improving the interpretability of convolution neural network [article]

Jinwei Zhao, Qizhou Wang, Fuqiang Zhang, Wanli Qiu, Yufei Wang, Yu Liu, Guo Xie, Weigang Ma, Bin Wang, Xinhong Hei
2019 arXiv   pre-print
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
more » ... te 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.
arXiv:1910.09090v1 fatcat:wubqlyj44vabzgbgxmjaigjn3y