Correspondence between neuroevolution and gradient descent

doi:10.1038/s41467-021-26568-2

Original source · Paper JSON

NeuroAI · 2021-11-02

Cites (1) · Cited by (0)

Complete cleaned Markdown · Source Markdown including bibliography

Read in parts

1. Part 1
2. Part 2
3. Part 3

Contents

• Correspondence between neuroevolution and gradient descent
• Abstract
• Similar content being viewed by others
• Gradient-based learning drives robust representations in recurrent neural networks by balancing compression and expansion
• Deep neural networks with controlled variable selection for the identification of putative causal genetic variants
• The neural coding framework for learning generative models
• Explore related subjects
• Introduction
• Results
• Gradient descent
• Neuroevolution
• Discussion
• Numerical illustration of the neuroevolution-gradient descent correspondence
• Shallow net, β = ∞
• Deep net, β = ∞
• Shallow net, finite β
• Conclusions
• Methods
• Derivation of the neuroevolution-gradient descent correspondence
• The case of finite β
• The case β = ∞
• Data availability
• Code availability
• Supplementary information
• Supplementary Information (download PDF )
• Rights and permissions
• About this article
• Cite this article
• Share this article
• Search
• Quick links
• nature.com footer links
• About Nature Portfolio
• Discover content
• Publishing policies
• Author & Researcher services
• Libraries & institutions
• Advertising & partnerships
• Professional development
• Regional websites