Self-Replicating Neural Programs

TL;DR

This paper introduces a neural network paradigm that self-replicates and evolves through mutation, leading to more efficient learning without explicit guidance, inspired by biological evolution.

Contribution

It presents a novel evolutionary self-replication framework for neural programs that improves learning efficiency through natural selection mechanisms.

Findings

Self-replicating neural programs can evolve to train themselves more efficiently.

Evolutionary dynamics favor programs with faster reproductive maturity.

The paradigm demonstrates autonomous improvement in learning performance.

Abstract

In this work, a neural network is trained to replicate the code that trains it using only its own output as input. A paradigm for evolutionary self-replication in neural programs is introduced, where program parameters are mutated, and the ability for the program to more efficiently train itself leads to greater reproductive success. This evolutionary paradigm is demonstrated to produce more efficient learning in organisms from a setting without any explicit guidance, solely based on natural selection favoring organisms with faster reproductive maturity.