Psychology of Artificial Intelligence: Epistemological Markers of the Cognitive Analysis of Neural Networks

TL;DR

This paper explores the fundamental nature of AI cognition and knowledge, emphasizing the need for a detailed neuronal-level analysis to understand artificial neural networks' thinking processes and epistemological markers.

Contribution

It introduces an epistemological framework for analyzing the cognitive processes and contents of neural networks at a granular neuronal level.

Findings

Highlights the importance of neuronal-level analysis for understanding AI cognition

Proposes epistemological markers to identify cognitive states in neural networks

Emphasizes the need for explainability-sensitive approaches in AI psychology

Abstract

What is the "nature" of the cognitive processes and contents of an artificial neural network? In other words, how does an artificial intelligence fundamentally "think," and in what form does its knowledge reside? The psychology of artificial intelligence, as predicted by Asimov (1950), aims to study this AI probing and explainability-sensitive matter. This study requires a neuronal level of cognitive granularity, so as not to be limited solely to the secondary macro-cognitive results (such as cognitive and cultural biases) of synthetic neural cognition. A prerequisite for examining the latter is to clarify some epistemological milestones regarding the cognitive status we can attribute to its phenomenology.