Neuropsychology and Explainability of AI: A Distributional Approach to the Relationship Between Activation Similarity of Neural Categories in Synthetic Cognition

TL;DR

This paper introduces a neuropsychological approach to AI explainability, using human cognitive psychology concepts like categorization and similarity to interpret neural network activation patterns and their categorical convergence.

Contribution

It proposes a novel framework linking human cognitive concepts to neural network activation similarity, enhancing interpretability through a distributional approach.

Findings

Neural categorical convergence reflects superposition of sub-dimensions.

Activation similarity can be used as a heuristic for explainability.

The approach bridges human cognition and artificial neural processing.

Abstract

We propose a neuropsychological approach to the explainability of artificial neural networks, which involves using concepts from human cognitive psychology as relevant heuristic references for developing synthetic explanatory frameworks that align with human modes of thought. The analogical concepts mobilized here, which are intended to create such an epistemological bridge, are those of categorization and similarity, as these notions are particularly suited to the categorical "nature" of the reconstructive information processing performed by artificial neural networks. Our study aims to reveal a unique process of synthetic cognition, that of the categorical convergence of highly activated tokens. We attempt to explain this process with the idea that the categorical segment created by a neuron is actually the result of a superposition of categorical sub-dimensions within its input vector space.