.png){kind=icon}
返回
Explaining Deep Learning Models Through Rule-Based Approximation and Visualization
.png){kind=icon}
OA
AI
DOI：10.1109/TFUZZ.2020.2999776.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This article describes a novel approach to the problem of developing explainable machine learning models. We consider a deep reinforcement learning (DRL) model representing a highway path planning policy for autonomous highway driving [1]. The model constitutes a mapping from the continuous multidimensional state space characterizing vehicle positions and velocities to a discrete set of actions in longitudinal and lateral direction. It is obtained by applying a customized version of the double deep Q-network learning algorithm [2]. The main idea is to approximate the DRL model with a set of IF-THEN rules that provide an alternative interpretable model, which is further enhanced by visualizing the rules. This concept is rationalized by the universal approximation properties of the rule-based models with fuzzy predicates. The proposed approach includes a learning engine composed of zero-order fuzzy rules, which generalize locally around the prototypes by using multivariate function models. The adjacent (in the data space) prototypes, which correspond to the same action, are further grouped and merged into the so-called MegaClouds reducing significantly the number of fuzzy rules. The input selection method is based on ranking the density of the individual inputs. Experimental results show that the specific DRL agent can be interpreted by approximating with families of rules of different granularity. The method is computationally efficient and can be potentially extended to addressing the explainability of the broader set of fully connected deep neural network models.
Keyword:
Autonomous driving
deep reinforcement learning
density-based input selection
explainable artificial intelligence
prototype- and density-based models
rule-based models
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:
11.9
论文数:
5.0K
被引数:
2.9W
机构
引用论文
分享收藏Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead停止解释高风险决策的黑盒机器学习模型，而改用可解释的模型OAAI
OAAI分享收藏分享收藏分享收藏The RHOA G17V gene mutation occurs frequently in peripheral T-cell lymphoma and is associated with a characteristic molecular signatureRHOA G17V基因突变在外周T细胞淋巴瘤中经常发生，并与特征性分子特征相关.png)
BloodOAAI
BloodIF0
OAAI分享收藏
查看更多内容