Evolutionary aspects of Reservoir Computing

Abstract

Reservoir Computing (RC) is a powerful computational paradigm that allows high versatility with cheap learning. While other artificial intelligence approaches need exhaustive resources to specify their inner workings, RC is based on a reservoir with highly non-linear dynamics that does not require a fine tuning of its parts. These dynamics project input signals into high-dimensional spaces, where training linear readouts to extract input features is vastly simplified. Thus, inexpensive learning provides very powerful tools for decision making, controlling dynamical systems, classification, etc. RC also facilitates solving multiple tasks in parallel, resulting in a high throughput. Existing literature focuses on applications in artificial intelligence and neuroscience. We review this literature from an evolutionary perspective. RC's versatility make it a great candidate to solve outstanding problems in biology, which raises relevant questions: Is RC as abundant in Nature as its advantages should imply? Has it evolved? Once evolved, can it be easily sustained? Under what circumstances? (In other words, is RC an evolutionarily stable computing paradigm?) To tackle these issues we introduce a conceptual morphospace that would map computational selective pressures that could select for or against RC and other computing paradigms. This guides a speculative discussion about the questions above and allows us to propose a solid research line that brings together computation and evolution with RC as a working bench.

arXiv comment17 pages, 4 figures, review paper

References in corpus (13)

• On the difficulty of training Recurrent Neural Networks
• Emergent complex neural dynamics
• Are biological systems poised at criticality?
• Colloquium: Criticality and dynamical scaling in living systems
• Information-based fitness and the emergence of criticality in living systems
• On the Origins of Hierarchy in Complex Networks
• The use of information theory in evolutionary biology
• Local Dynamics in Trained Recurrent Neural Networks
• High accuracy decoding of dynamical motion from a large retinal population
• Determination of the edge of criticality in echo state networks through Fisher information maximization
• Phase transitions in Pareto optimal complex networks
• On the basic computational structure of gene regulatory networks
• Detection of Generalized Synchronization using Echo State Networks