mlsanityData to 14 Oct 2026

HyperNCA: Growing Developmental Networks with Neural Cellular Automata

arXiv 2204.11674 ↗First posted 25 Apr 2022cs.NE cs.AI cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 16 of its 42 references that are in the map. First posted on arXiv 25 Apr 2022.

Builds on

16 of 42 references.

References · 16

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2016HyperNetworkscited by 1,027
  3. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
  4. 2017A Brief Survey of Deep Reinforcement Learningcited by 483
  5. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 371
  6. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 150
  7. 2015Neural GPUs Learn Algorithmscited by 121
  8. 2013Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robotscited by 58
  9. 2022HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learningcited by 55
  10. 2020Meta-Learning through Hebbian Plasticity in Random Networkscited by 47
  11. 2018Cellular automata as convolutional neural networkscited by 45
  12. 2021Growing 3D Artefacts and Functional Machines with Neural Cellular Automatacited by 38
4 more
  1. 2021Collective Intelligence for Deep Learning: A Survey of Recent Developmentscited by 34
  2. 2019Deep Neuroevolution of Recurrent and Discrete World Modelscited by 23
  3. 2021Evolving and Merging Hebbian Learning Rules: Increasing Generalization by Decreasing the Number of Rulescited by 12
  4. 2017A Minimal Developmental Model Can Increase Evolvability in Soft Robotscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 5; 2025: 5; 2026: 4.

18 papers.

Sort:

By area:

  1. 2022Attention-based Neural Cellular Automatacited by 26
  2. 2024On the limits of agency in agent-based modelscited by 21
  3. 2023Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programscited by 17
  4. 2025Neural cellular automata: applications to biology and beyond classical AIcited by 9
  5. 2023Self-Replication, Spontaneous Mutations, and Exponential Genetic Drift in Neural Cellular Automatacited by 8
  6. 2024CAX: Cellular Automata Accelerated in JAXcited by 8
  7. 2025EngramNCA: a Neural Cellular Automaton Model of Memory Transfercited by 7
  8. 2024Heuristically Adaptive Diffusion-Model Evolutionary Strategycited by 6
  9. 2025A Path to Universal Neural Cellular Automatacited by 6
  10. 2024Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learningcited by 4
  11. 2023Synaptic motor adaptation: A three-factor learning rule for adaptive robotic control in spiking neural networkscited by 3
  12. 2024Evolved Developmental Artificial Neural Networks for Multitasking with Advanced Activity Dependencecited by 2
6 more
  1. 2025When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?cited by 2
  2. 2025Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticitycited by 1
  3. 2026Remapping and navigation of an embedding space via error minimization: a fundamental organizational principle of cognition in natural and artificial systemscited by 1
  4. 2026Architecture Generalization with MetaNCAcited by 0
  5. 2026On Growth and Form, and Function: Reusable Regulatory Handles Control Phenotypic Variationcited by 0
  6. 2026Where Does Randomness Matter in Neural Cellular Automata?cited by 0