Rights statement: ©2020 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Accepted author manuscript, 834 KB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Explaining Deep Learning Models Through Rule-Based Approximation and Visualization
AU - Almeida Soares, Eduardo
AU - Angelov, Plamen
AU - Costa, Bruno
AU - Castro, Marcos
AU - Nageshrao, Subramanya
AU - Filev, Dimitar
N1 - ©2020 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
PY - 2021/8/31
Y1 - 2021/8/31
N2 - This paper 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. 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 (DDQN) learning algorithm. 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 0-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 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
AB - This paper 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. 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 (DDQN) learning algorithm. 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 0-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 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
KW - Deep Reinforcement Learning
KW - explainable AI
KW - rule-based models
KW - prototype- and density-based models
KW - density-based input selection
KW - autonomous driving
U2 - 10.1109/TFUZZ.2020.2999776
DO - 10.1109/TFUZZ.2020.2999776
M3 - Journal article
VL - 29
SP - 2399
EP - 2407
JO - IEEE Transactions on Fuzzy Systems
JF - IEEE Transactions on Fuzzy Systems
SN - 1063-6706
IS - 8
ER -