Self-Organizing Intelligent Matter: A blueprint for an AI generating algorithm
arXiv:2101.07627
Abstract
We propose an artificial life framework aimed at facilitating the emergence of intelligent organisms. In this framework there is no explicit notion of an agent: instead there is an environment made of atomic elements. These elements contain neural operations and interact through exchanges of information and through physics-like rules contained in the environment. We discuss how an evolutionary process can lead to the emergence of different organisms made of many such atomic elements which can coexist and thrive in the environment. We discuss how this forms the basis of a general AI generating algorithm. We provide a simplified implementation of such system and discuss what advances need to be made to scale it up further.
13 pages, 2 figures
References in corpus (12)
- Neural Architecture Search with Reinforcement Learning
- Neural Architecture Search: A Survey
- Efficient Neural Architecture Search via Parameter Sharing
- Illuminating search spaces by mapping elites
- AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
- Cellular automata as convolutional neural networks
- Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
- AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
- Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
- Automated curricula through setter-solver interactions
- Finding online neural update rules by learning to remember
- Network of Evolvable Neural Units: Evolving to Learn at a Synaptic Level