The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916631746183168 |
|---|---|
| author | Pichat, Michael Pogrund, William Gasparian, Armanush Pichat, Paloma Demarchi, Samuel Veillet-Guillem, Michael Corbet, Martin Dasilva, Théo |
| author_facet | Pichat, Michael Pogrund, William Gasparian, Armanush Pichat, Paloma Demarchi, Samuel Veillet-Guillem, Michael Corbet, Martin Dasilva, Théo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15710 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognition Pichat, Michael Pogrund, William Gasparian, Armanush Pichat, Paloma Demarchi, Samuel Veillet-Guillem, Michael Corbet, Martin Dasilva, Théo Artificial Intelligence Neurons and Cognition 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. |
| title | The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognition |
| topic | Artificial Intelligence Neurons and Cognition |
| url | https://arxiv.org/abs/2502.15710 |