The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognition
This work addresses the problem of understanding concept formation in AI for neuropsychology researchers, but it appears incremental as it builds on existing neural network mechanisms without demonstrating broad advancements.
The paper investigates how language models create new categorical dimensions through a process called categorical clipping, which involves selective extraction of subdimensions from neural layers to form concepts, but it does not report concrete numerical results or performance gains.
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.