Low-Order Model of Biological Neural Networks

TL;DR

This paper introduces a biologically plausible low-order model of neural networks that can learn and recognize complex patterns without traditional optimization, mimicking real neural processes.

Contribution

It presents a novel low-order model incorporating dendritic structures, diverse neuron types, and learning mechanisms for efficient pattern recognition.

Findings

Model learns and retrieves patterns without differentiation or iteration.

Capable of recognizing hierarchical and corrupted patterns.

Supports both supervised and unsupervised learning.

Abstract

A biologically plausible low-order model (LOM) of biological neural networks is a recurrent hierarchical network of dendritic nodes/trees, spiking/nonspiking neurons, unsupervised/ supervised covariance/accumulative learning mechanisms, feedback connections, and a scheme for maximal generalization. These component models are motivated and necessitated by making LOM learn and retrieve easily without differentiation, optimization, or iteration, and cluster, detect and recognize multiple/hierarchical corrupted, distorted, and occluded temporal and spatial patterns.