arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1910.09090cs.LGcs.CVstat.ML
收藏

一种提高卷积神经网络可解释性的博弈方法

A game method for improving the interpretability of convolution neural network

Faculty of Computer Science and Engineering, Xi’an University of Technology(西安理工大学计算机科学与工程学院);Faculty of Science, Xi’an University of Technology(西安理工大学理学院)

Jinwei Zhao, Qizhou Wang, Fuqiang Zhang, Wanli Qiu, Yufei Wang, Yu Liu, Guo Xie, Weigang Ma, Bin Wang, Xinhong Hei

摘要:

真正的人工智能一直是机器学习研究者关注的焦点,特别是在深度学习领域。然而,深层的神经网络是难以理解和解释的,有时甚至是形而上学。原因在于,我们认为:网络本质上是一种感知模型。因此,我们认为,要从简单的感知完成复杂的智能活动,就必须构建另一个可解释的逻辑网络,形成对外界事物的准确、合理的反应和解释。像Bolei Zhou和Quanshi Zhang这样的研究人员针对卷积神经网络的特征提取阶段,发现了许多深度特征提取的解释规则。然而,尽管像Marco Gori这样的研究人员也在努力提高网络全连接层的可解释性,但问题也非常困难。本文首先分析了其原因。提出了一种基于全连通层的逻辑网络构造方法,并提取了各层输入输出之间的逻辑关系。实现了感知学习与逻辑抽象认知学习的博弈过程,提高了深度学习过程和深度学习模型的可解释性。我们的方法的好处是说明基准数据集和现实世界的实验。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑