On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysis

A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would help answer the question of what a deep learning system internally detects as relevant in the input, demystifying the otherwise black-box nature of deep learning systems. Th...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Dalal, Abhilekha, Rushrukh Rayan, Barua, Adrita, Vasserman, Eugene Y, Md Kamruzzaman Sarker, Hitzler, Pascal
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 21.04.2024
Subjects
Activation analysis
Artificial neural networks
Deep learning
Explainable artificial intelligence
Machine learning
Neurons
Statistical analysis
Online AccessGet full text

Cover

More Information
Summary:A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would help answer the question of what a deep learning system internally detects as relevant in the input, demystifying the otherwise black-box nature of deep learning systems. The state of the art indicates that hidden node activations can, in some cases, be interpretable in a way that makes sense to humans, but systematic automated methods that would be able to hypothesize and verify interpretations of hidden neuron activations are underexplored. This is particularly the case for approaches that can both draw explanations from substantial background knowledge, and that are based on inherently explainable (symbolic) methods. In this paper, we introduce a novel model-agnostic post-hoc Explainable AI method demonstrating that it provides meaningful interpretations. Our approach is based on using a Wikipedia-derived concept hierarchy with approximately 2 million classes as background knowledge, and utilizes OWL-reasoning-based Concept Induction for explanation generation. Additionally, we explore and compare the capabilities of off-the-shelf pre-trained multimodal-based explainable methods. Our results indicate that our approach can automatically attach meaningful class expressions as explanations to individual neurons in the dense layer of a Convolutional Neural Network. Evaluation through statistical analysis and degree of concept activation in the hidden layer show that our method provides a competitive edge in both quantitative and qualitative aspects compared to prior work.
ISSN:2331-8422