Evolving Self-supervised Neural Networks: Autonomous Intelligence from Evolved Self-teaching
Year: 2019
Type: preprint
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.
Source: arXiv (Cornell University)
Author: Le, Nam
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2949936448