How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic Neurons
This work addresses the fundamental problem of understanding artificial cognition mechanisms for researchers in AI and cognitive science, but it appears incremental as it builds on existing concepts without clear new applications.
The paper investigates how synthetic neurons in language models form thought categories to segment information, identifying three mathematico-cognitive factors—priming, attention, and categorical phasing—based on algebraic operations in neuronal functions.
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.