HyperNCA: Growing Developmental Networks with Neural Cellular Automata

Publikation: Artikel i tidsskrift og konference artikel i tidsskriftKonferenceartikelForskningpeer review

Abstract

In contrast to deep reinforcement learning agents, biological neural networks are grown through a self-organized developmental process. Here we propose a new hypernetwork approach to grow artificial neural networks based on neural cellular automata (NCA). Inspired by self-organising systems and information-theoretic approaches to developmental biology, we show that our HyperNCA method can grow neural networks capable of solving common reinforcement learning tasks. Finally, we explore how the same approach can be used to build developmental metamorphosis networks capable of transforming their weights to solve variations of the initial RL task.
OriginalsprogEngelsk
TidsskriftarXiv
ISSN2331-8422
StatusUdgivet - 2022

Emneord

  • self-organized developmental process
  • neural cellular automata
  • HyperNCA
  • biological neural networks
  • metamorphosis networks

Fingeraftryk

Dyk ned i forskningsemnerne om 'HyperNCA: Growing Developmental Networks with Neural Cellular Automata'. Sammen danner de et unikt fingeraftryk.

Citationsformater