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

TL;DR

The paper introduces a neural network model called ChatSOME that explains how humans learn and understand large language models through brain-like processes.

Contribution

The novel contribution is the development of ChatSOME, a model that integrates brain-inspired learning mechanisms to explain human-like understanding of language and meaning.

Findings

ChatSOME uses adaptive resonance theory to enable self-stabilizing memory and learning of perceptual and emotional meanings.

The model explains how humans learn to recognize an unlimited number of visual scenes and associate them with language and emotions.

Unlike AI models like ChatGPT, ChatSOME incorporates joint attention, emotion, and reinforcement learning to simulate human-like cognition.

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.

Figures