Skip to Main content Skip to Navigation
Theses

Evolving principes of artificial neural design

Dennis G. Wilson 1
1 IRIT-REVA - Real Expression Artificial Life
IRIT - Institut de recherche en informatique de Toulouse
Abstract : The biological brain is an ensemble of individual components which have evolved over millions of years. Neurons and other cells interact in a complex network from which intelligence emerges. Many of the neural designs found in the biological brain have been used in computational models to power artificial intelligence, with modern deep neural networks spurring a revolution in computer vision, machine translation, natural language processing, and many more domains. However, artificial neural networks are based on only a small subset of biological functionality of the brain, and often focus on global, homogeneous changes to a system that is complex and locally heterogeneous. In this work, we examine the biological brain, from single neurons to networks capable of learning. We examine individually the neural cell, the formation of connections between cells, and how a network learns over time. For each component, we use artificial evolution to find the principles of neural design that are optimized for artificial neural networks. We then propose a functional model of the brain which can be used to further study select components of the brain, with all functions designed for automatic optimization such as evolution. Our goal, ultimately, is to improve the performance of artificial neural networks through inspiration from modern neuroscience. However, through evaluating the biological brain in the context of an artificial agent, we hope to also provide models of the brain which can serve biologists.
Document type :
Theses
Complete list of metadata

Cited literature [243 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-02930188
Contributor : Abes Star :  Contact Connect in order to contact the contributor
Submitted on : Friday, September 4, 2020 - 11:22:07 AM
Last modification on : Thursday, June 10, 2021 - 3:08:01 AM
Long-term archiving on: : Wednesday, December 2, 2020 - 8:18:22 PM

File

2019TOU30075b.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02930188, version 1

Citation

Dennis G. Wilson. Evolving principes of artificial neural design. Artificial Intelligence [cs.AI]. Université Paul Sabatier - Toulouse III, 2019. English. ⟨NNT : 2019TOU30075⟩. ⟨tel-02930188⟩

Share

Metrics

Record views

90

Files downloads

273