Self-Assembling Artificial Neural Networks Through Neural Developmental Programs

[Submitted on 17 Jul 2023]

Title:Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs

Download a PDF of the paper titled Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs, by Elias Najarro and 2 other authors

Download PDF

Abstract:Biological nervous systems are created in a fundamentally different way than current artificial neural networks. Despite its impressive results in a variety of different domains, deep learning often requires considerable engineering effort to design high-performing neural architectures. By contrast, biological nervous systems are grown through a dynamic self-organizing process. In this paper, we take initial steps toward neural networks that grow through a developmental process that mirrors key properties of embryonic development in biological organisms. The growth process is guided by another neural network, which we call a Neural Developmental Program (NDP) and which operates through local communication alone. We investigate the role of neural growth on different machine learning benchmarks and different optimization methods (evolutionary training, online RL, offline RL, and supervised learning). Additionally, we highlight future research directions and opportunities enabled by having self-organization driving the growth of neural networks.

Submission history

From: Sebastian Risi [view email]

[v1] Mon, 17 Jul 2023 01:58:52 UTC (14,847 KB)

from Hacker News https://ift.tt/A5RZmPb