Neural network models of autonomous adaptive intelligence and artificial general intelligence: how our brains learn large language models and their meanings.

A biological neural network model called ChatSOME (Self-Organizing MEaning) explains how humans learn to understand large language models and their meanings through teacher-student interactions. Multiple self-organizing brain processes are involved, including content-addressable memory, conscious visual perception, joint attention, object learning, categorization, cognition, cognitive working memory, planning, neural-symbolic computing, emotion, cognitive-emotional interactions, reinforcement learning, volition, and goal-oriented actions. The model extends earlier work on small language models with perceptual and affective meanings, now explaining how humans consciously see and recognize unlimited visual scenes. Bi-directional associative links between scenes, emotions, and language utterances are learned and stably remembered via adaptive resonance theory circuits. These human capabilities are not found in AI models such as ChatGPT.

Study at a glance

Abstract

This article describes a biological neural network model that explains how humans learn to understand large language models and their meanings. This kind of learning typically occurs when a student learns from a teacher about events that they experience together. Multiple types of self-organizing brain processes are involved, including content-addressable memory; conscious visual perception; joint attention; object learning, categorization, and cognition; conscious recognition; cognitive working memory; cognitive planning; neural-symbolic computing; emotion; cognitive-emotional interactions and reinforcement learning; volition; and goal-oriented actions. The article advances earlier results showing how small language models are learned that have perceptual and affective meanings. The current article explains how humans, and neural network models thereof, learn to consciously see and recognize an unlimited number of visual scenes. Then, bi-directional associative links can be learned and stably remembered between these scenes, the emotions that they evoke, and the descriptive language utterances associated with them. Adaptive resonance theory circuits control model learning and self-stabilizing memory. These human capabilities are not found in AI models such as ChatGPT. The current model is called ChatSOME, where SOME abbreviates Self-Organizing MEaning. The article summarizes neural network highlights since the 1950s and leading models, including adaptive resonance, deep learning, LLMs, and transformers.