Info-Evo: Using Information Geometry to Guide Evolutionary Program Learning

2021/02/20 by Ben Goertzel, Goertzel, Ben · 1 citation
Computer Science · #Advanced Multi-Objective Optimization Algorithms #Artificial Intelligence (cs.AI) #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Metaheuristic Optimization Algorithms Research #Neural and Evolutionary Computing (cs.NE)

paper · pdf · doi:10.48550/arxiv.2103.04747

openalex publication_date 2021/02/20 · openalex created_date 2021/04/13 · openalex updated_date 2026/07/28

Abstract

A novel optimization strategy, Info-Evo, is described, in which natural gradient search using nonparametric Fisher information is used to provide ongoing guidance to an evolutionary learning algorithm, so that the evolutionary process preferentially moves in the directions identified as "shortest paths" according to the natural gradient. Some specifics regarding the application of this approach to automated program learning are reviewed, including a strategy for integrating Info-Evo into the MOSES program learning framework.

Cited by

• Evolutionary Computation as Natural Generative AI

Related

• Learning Evolution via Optimization Knowledge Adaptation
• Avoiding the Bloat with Stochastic Grammar-based Genetic Programming
• Evaluating evolution as a learning algorithm
• EDOLAB: An Open-Source Platform for Education and Experimentation with Evolutionary Dynamic Optimization Algorithms
• Genome as a functional program