Evolving Self-supervised Neural Networks: Autonomous Intelligence from Evolved Self-teaching

Abstract

This paper presents a technique called evolving self-supervised neural networks - neural networks that can teach themselves, intrinsically motivated, without external supervision or reward. The proposed method presents some sort-of paradigm shift, and differs greatly from both traditional gradient-based learning and evolutionary algorithms in that it combines the metaphor of evolution and learning, more specifically self-learning, together, rather than treating these phenomena alternatively. I simulate a multi-agent system in which neural networks are used to control autonomous foraging agents with little domain knowledge. Experimental results show that only evolved self-supervised agents can demonstrate some sort of intelligent behaviour, but not evolution or self-learning alone. Indications for future work on evolving intelligence are also presented.

11. arXiv admin note: text overlap with arXiv:1906.08854

References in corpus (8)

• Deep Learning in Neural Networks: An Overview
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
• Innateness, AlphaZero, and Artificial Intelligence
• Meta-Learning by the Baldwin Effect
• Evolving Self-taught Neural Networks: The Baldwin Effect and the Emergence of Intelligence