Towards self-organized control
One of the most remarkable feats of life is the developmental process leading to the emergent complexity of the human brain from a single cell. The field of neurodevelopment (i.e., the development of the nervous system) has been investigating this problem for decades. These studies led to the discovery of the intricate mechanisms by which gradients of chemicals and local cell interactions shape the differentiation of pre-neural cells and the organization of their connections [1].
Towards self-organized control Towards self-organized control Using neural cellular automata to robustly control a cart-pole agent Alexandre Variengien 1,2,3 , Sidney Pontes-Filho 1,4 , Tom Glover 1 , Stefano Nichele 1,2,* 1 Department of Computer Science, Oslo Metropolitan University, Oslo (Norway) 2 Department of Holistic Systems, Simula Metropolitan Centre for Digital Engineering, Oslo (Norway) 3 Department of Computer Science, École Normale Supérieure de Lyon, Lyon (France) 4 Department of Computer Science, Norwegian University of Science and Technology, Trondheim (Norway) * Corresponding
saved by
related reading
- Learning Sensorimotor Capabilities in Cellular Automatadevelopmentalsystems.org
- The World Inside Neural Networksgoodfire.ai
- [2506.22899] Neural Cellular Automata: From Cells to Pixelsarxiv.org
- pdfopenreview.net
- How our data shaped neural architecture discovery, and how automation can reshape the future | Core Automationcoreauto.com
- Human-like Neural Nets by Catapulting · Gwern.netgwern.net
- Could a computer scientist build a brain?stankerstjens.github.io
- Learning Beyond Gradientstrinkle23897.github.io
- The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learningattentionneuron.github.io
- Self-Assembly Gets Automated in Reverse of ‘Game of Life’ | Quanta Magazinequantamagazine.org
- The worminator project postpreprintarxiv.org
- Unexpected Benefits of Self-Modeling in Neural Systemsarxiv.org