The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognition

TL;DR

This paper explores how neural networks perform categorical segmentation through a process called clipping, creating new categories by selectively extracting subdimensions, which sheds light on concept formation in artificial cognition.

Contribution

It introduces the concept of categorical clipping in neural networks, detailing how new categories are formed across layers via priming, attention, and phasing, advancing understanding of synthetic concept genesis.

Findings

Categorical clipping enables the formation of new categories from existing ones.

Neural layers use priming, attention, and phasing to guide category creation.

The process demonstrates characteristics like reduction, selectivity, and segmentation of categories.

Abstract

This article investigates, within the field of neuropsychology of artificial intelligence, the process of categorical segmentation performed by language models. This process involves, across different neural layers, the creation of new functional categorical dimensions to analyze the input textual data and perform the required tasks. Each neuron in a multilayer perceptron (MLP) network is associated with a specific category, generated by three factors carried by the neural aggregation function: categorical priming, categorical attention, and categorical phasing. At each new layer, these factors govern the formation of new categories derived from the categories of precursor neurons. Through a process of categorical clipping, these new categories are created by selectively extracting specific subdimensions from the preceding categories, constructing a distinction between a form and a categorical background. We explore several cognitive characteristics of this synthetic clipping in an exploratory manner: categorical reduction, categorical selectivity, separation of initial embedding dimensions, and segmentation of categorical zones.