Dimensions of Timescales in Neuromorphic Computing Systems

Abstract

This article is a public deliverable of the EU project "Memory technologies with multi-scale time constants for neuromorphic architectures" (MeMScales, https://memscales.eu, Call ICT-06-2019 Unconventional Nanoelectronics, project number 871371). This arXiv version is a verbatim copy of the deliverable report, with administrative information stripped. It collects a wide and varied assortment of phenomena, models, research themes and algorithmic techniques that are connected with timescale phenomena in the fields of computational neuroscience, mathematics, machine learning and computer science, with a bias toward aspects that are relevant for neuromorphic engineering. It turns out that this theme is very rich indeed and spreads out in many directions which defy a unified treatment. We collected several dozens of sub-themes, each of which has been investigated in specialized settings (in the neurosciences, mathematics, computer science and machine learning) and has been documented in its own body of literature. The more we dived into this diversity, the more it became clear that our first effort to compose a survey must remain sketchy and partial. We conclude with a list of insights distilled from this survey which give general guidelines for the design of future neuromorphic systems.

References in corpus (13)

• Recent Advances in Physical Reservoir Computing: A Review
• A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)
• Neuromorphic electronic circuits for building autonomous cognitive systems
• A magnetic skyrmion as a non-linear resistive element - a potential building block for reservoir computing
• Spatio-temporal phenomena in complex systems with time delays
• Computing with Networks of Nonlinear Mechanical Oscillators
• Controlling Recurrent Neural Networks by Conceptors
• Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets
• Exploring the landscapes of "computing": digital, neuromorphic, unconventional -- and beyond
• Task Agnostic Continual Learning via Meta Learning
• Delayed Dynamical Systems: Networks, Chimeras and Reservoir Computing
• Reservoirs learn to learn
• Random pattern and frequency generation using a photonic reservoir computer with output feedback

Cited by in corpus (3)

• Exploring the landscapes of "computing": digital, neuromorphic, unconventional -- and beyond
• Integration of Neuromorphic AI in Event-Driven Distributed Digitized Systems: Concepts and Research Directions
• Exploring Non-Steady-State Charge Transport Dynamics in Information Processing: Insights from Reservoir Computing