Orangutan: A Multiscale Brain Emulation-Based Artificial Intelligence Framework for Dynamic Environments

TL;DR

This paper presents Orangutan, a brain-inspired AI framework that emulates multiscale neural structures and biochemical processes to advance towards general artificial intelligence, demonstrated through a sensorimotor model of eye movements.

Contribution

The paper introduces a comprehensive multiscale brain emulation framework, integrating neural and biochemical mechanisms grounded in neuroscience for AI development.

Findings

Validated sensorimotor model simulating human eye movements.

Effective recognition of handwritten digit images.

Demonstrated potential for general AI through brain-inspired mechanisms.

Abstract

Achieving General Artificial Intelligence (AGI) has long been a grand challenge in the field of AI, and brain-inspired computing is widely acknowledged as one of the most promising approaches to realize this goal. This paper introduces a novel brain-inspired AI framework, Orangutan. It simulates the structure and computational mechanisms of biological brains on multiple scales, encompassing multi-compartment neuron architectures, diverse synaptic connection modalities, neural microcircuits, cortical columns, and brain regions, as well as biochemical processes including facilitation, feedforward inhibition, short-term potentiation, and short-term depression, all grounded in solid neuroscience. Building upon these highly integrated brain-like mechanisms, I have developed a sensorimotor model that simulates human saccadic eye movements during object observation. The model's algorithmic efficacy was validated through testing with the observation of handwritten digit images.