From Artificial Intelligence to Brain Intelligence: The basis learning and memory algorithm for brain-like intelligence

TL;DR

This paper introduces a biologically plausible brain-inspired learning algorithm that adapts backpropagation for neural networks, incorporating memory engram encoding and simulating hippocampal memory functions.

Contribution

It presents a novel brain-compatible backpropagation algorithm and an encoding method for memory engrams, bridging artificial learning with biological neural processes.

Findings

Successful implementation of image classification with brain-like backpropagation

Proposed encoding algorithm simulates hippocampal fast associative memory

Explained the roles of LTP and LTD in cerebellum at the algorithm level

Abstract

The algorithm of brain learning and memory is still undetermined. The backpropagation algorithm of artificial neural networks was thought not suitable for brain cortex, and there is a lack of algorithm for memory engram. We designed a brain version of backpropagation algorithm, which are biologically plausible and could be implemented with virtual neurons to complete image classification task. An encoding algorithm that can automatically allocate engram cells is proposed, which is an algorithm implementation for memory engram theory, and could simulate how hippocampus achieve fast associative memory. The role of the LTP and LTD in the cerebellum is also explained in algorithm level. Our results proposed a method for the brain to deploy backpropagation algorithm, and sparse coding method for memory engram theory.