How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic Neurons

TL;DR

This paper investigates how synthetic neurons in language models form 'thought categories' by analyzing the mathematical and cognitive factors like priming, attention, and categorical phasing that influence artificial cognition.

Contribution

It introduces a novel framework linking algebraic neuronal functions to cognitive processes, revealing the mathematical basis of categorical segmentation in AI.

Findings

Identification of three key mathematico-cognitive factors: priming, attention, and categorical phasing.

Mathematical analysis of neuronal aggregation functions elucidates how categories are formed.

Proposes a new perspective on the cognitive characteristics of artificial neurons.

Abstract

How do the synthetic neurons in language models create "thought categories" to segment and analyze their informational environment? What are the cognitive characteristics, at the very level of formal neurons, of this artificial categorical thought? Based on the mathematical nature of algebraic operations inherent to neuronal aggregation functions, we attempt to identify mathematico-cognitive factors that genetically shape the categorical reconstruction of the informational world faced by artificial cognition. This study explores these concepts through the notions of priming, attention, and categorical phasing.