Unsupervised Learning in Complex Systems

TL;DR

This thesis investigates how complex systems can facilitate unsupervised learning and adaptation, introducing new metrics and methods to analyze growth of complexity and learning efficiency in natural and artificial systems.

Contribution

It develops a general complexity metric, a coarse-graining method for large systems, and a benchmark dataset for evaluating learning speed, advancing understanding of learning in complex systems.

Findings

Added understanding of learning and adaptation in complex systems

Introduced a new complexity metric for system analysis

Provided a benchmark for learning efficiency evaluation

Abstract

In this thesis, we explore the use of complex systems to study learning and adaptation in natural and artificial systems. The goal is to develop autonomous systems that can learn without supervision, develop on their own, and become increasingly complex over time. Complex systems are identified as a suitable framework for understanding these phenomena due to their ability to exhibit growth of complexity. Being able to build learning algorithms that require limited to no supervision would enable greater flexibility and adaptability in various applications. By understanding the fundamental principles of learning in complex systems, we hope to advance our ability to design and implement practical learning algorithms in the future. This thesis makes the following key contributions: the development of a general complexity metric that we apply to search for complex systems that exhibit growth of complexity, the introduction of a coarse-graining method to study computations in large-scale complex systems, and the development of a metric for learning efficiency as well as a benchmark dataset for evaluating the speed of learning algorithms. Our findings add substantially to our understanding of learning and adaptation in natural and artificial systems. Moreover, our approach contributes to a promising new direction for research in this area. We hope these findings will inspire the development of more effective and efficient learning algorithms in the future.