paper-with-me

홈 › Papers

Polysemy of Synthetic Neurons Towards a New Type of Explanatory Categorical Vector Spaces

2025-04-30 · Michael Pichat, William Pogrund, Paloma Pichat, Judicael Poumay, Armanouche Gasparian, Samuel Demarchi, Martin Corbet, Alois Georgeon, Michael Veillet-Guillem

The polysemantic nature of synthetic neurons in artificial intelligence language models is currently understood as the result of a necessary superposition of distributed features within the latent space. We propose an alternative approach, geometrically defining a neuron in layer n as a categorical vector space with a non-orthogonal basis, composed of categorical sub-dimensions extracted from preceding neurons in layer n-1. This categorical vector space is structured by the activation space of each neuron and enables, via an intra-neuronal attention process, the identification and utilization of a critical categorical zone for the efficiency of the language model - more homogeneous and located at the intersection of these different categorical sub-dimensions.

📄 PDF Abstract BibTeX arXiv:2505.07831

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Intra-neuronal attention within language models Relationships between activation and semantics

2025-03-17 · Michael Pichat, William Pogrund, Paloma Pichat, Armanouche Gasparian 외

This study investigates the ability of perceptron-type neurons in language models to perform intra-neuronal attention; that is, to identify different homogeneous categorical segments within the synthetic thought category…

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

2024-12-26 · Michael Pichat, William Pogrund, Armanush Gasparian, Paloma Pichat 외

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 art…

Neuropsychology and Explainability of AI: A Distributional Approach to the Relationship Between Activation Similarity of Neural Categories in Synthetic Cognition

2024-10-23 · Michael Pichat, Enola Campoli, William Pogrund, Jourdan Wilson 외

We propose a neuropsychological approach to the explainability of artificial neural networks, which involves using concepts from human cognitive psychology as relevant heuristic references for developing synthetic explan…

A Taxonomic Classification of WordNet Polysemy Types

2016-01-01 · GWC 2016 1 · Abed Alhakim Freihat, Fausto Giunchiglia, Biswanath Dutta

WordNet represents polysemous terms by capturing the different meanings of these terms at the lexical level, but without giving emphasis on the polysemy types such terms belong to. The state of the art polysemy approache…

Classification

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

2025-01-21 · Michael Pichat William Pogrund, Armanush Gasparian, Paloma Pichat, Samuel Demarchi 외

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 …