HESIP: a hybrid system for explaining sub-symbolic predictions

Abdus Salam*, Rolf Schwitter, Mehmet A. Orgun

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

Abstract

Machine learning models such as neural networks have been successfully used in many application domains such as mission critical systems, digital health and autonomous vehicles. It is important to understand why particular predictions are made by a sub-symbolic machine learning (ML) model, because humans use these predictions in their decision making process. In this paper, we introduce HESIP, a hybrid system that combines symbolic and sub-symbolic representations to explain a prediction in natural language for an image prediction task. A sub-symbolic ML model makes a prediction for an image, and based on this predicted image, the system selects sample images from the dataset. Afterwards, a symbolic ML model learns probabilistic rules using the representation of positive and negative sample image instances where the decision about a positive or negative image instance comes from the sub-symbolic ML model. The prediction of an image can then be explained in natural language using the learned rules. Our evaluation shows that the probabilistic rules can be learned with high accuracy.
Original languageEnglish
Title of host publicationAI 2021: Advances in Artificial Intelligence
Subtitle of host publication34th Australasian Joint Conference, AI 2021 Sydney, NSW, Australia, February 2–4, 2022, Proceedings
EditorsGuodong Long, Xinghuo Yu, Sen Wang
Place of PublicationCham, Switzerland
PublisherSpringer, Springer Nature
Pages27-39
Number of pages13
ISBN (Electronic)9783030975463
ISBN (Print)9783030975456
DOIs
Publication statusPublished - 2022
Event34th Australasian Joint Conference on Artificial Intelligence, AI 2022 - Sydney, Australia
Duration: 2 Feb 20224 Feb 2022

Publication series

NameLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
PublisherSpringer
Volume13151
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference34th Australasian Joint Conference on Artificial Intelligence, AI 2022
Country/TerritoryAustralia
CitySydney
Period2/02/224/02/22

Keywords

  • Explainability
  • Probabilistic rule learning
  • Symbolic machine learning

Fingerprint

Dive into the research topics of 'HESIP: a hybrid system for explaining sub-symbolic predictions'. Together they form a unique fingerprint.

Cite this