返回
High-precision linearized interpretation for fully connected neural network
DOI:10.1016/j.asoc.2021.107572.png)
摘要
En 中文
Despite the widespread application of deep neural networks in finance, medical treatment, and autonomous driving, these networks face multiple security threats, such as maliciously constructed adversarial samples that can easily mislead deep neural network model classification, causing errors. Therefore, creating an interpretable model or designing an interpretation method is necessary to improve its security. This paper presents an interpretation scheme, named Convergent Interpretation for Deep Neural Networks (CIDNN), to obtain a provably convergent and consistent interpretation for deep neural networks. The main idea of CIDNN is to first convert the deep neural networks into a set of mathematically convergent Piecewise Linear Neural Networks (PLNN), then convert the PLNN into a set of equivalent linear classifiers. In this way, each linear classifier can be interpreted by its decision features. By analyzing the convergence of the local approximation interpretation scheme, we prove that this interpretable model can be sufficiently close to the deep neural network with certain conditions. Experiments show the convergence of CIDNN's interpretation, and the interpretation conforms with similar samples in the synthetic dataset. Besides, we demonstrate the semantical meaning of CIDNN in the Fashion-MNIST dataset. (C) 2021 Elsevier B.V. All rights reserved.
Keyword:
Deep neural network
Convergent interpretation
Piecewise linear function
Sigmoid function
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.6
论文数:
1.4W
被引数:
4.8W
机构
引用论文
Transformative computing approaches for advanced management solutions and cognitive processing用于高级管理解决方案和认知处理的变革性计算方法
Transport of the phosphonodipeptide alafosfalin by the H+/peptide cotransporters PEPT1 and PEPT2 in intestinal and renal epithelial cells肠和肾上皮细胞中H/肽共转运蛋白PEPT1和PEPT2转运磷酰二肽阿拉非法林
SBBS: A Secure Blockchain-Based Scheme for IoT Data Credibility in Fog EnvironmentSBBS: 雾环境下基于区块链的物联网数据可信性安全方案
没有更多内容

