The Computational Capacity of Mem-LRC Reservoirs

Conference · Thu Jun 18 00:00:00 EDT 2020 · Proceedings of the Neuro-inspired Computational Elements Workshop

DOI:https://doi.org/10.1145/3381755.3381779· OSTI ID:1995142

Sheldon, Forrest Crawford ^[1]; Caravelli, Francesco ^[1]

---

1. Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Reservoir computing has a emerged as a powerful tool in data-driven time series analysis. The possibility of utilizing hardware reservoirs as specialized co-processors has generated interest in the properties of electronic reservoirs, especially those based on memristors as the nonlinearity of these devices should translate to an improved nonlinear computational capacity of the reservoir. However, designing these reservoirs requires a detailed understanding of how memristive networks process information which has thus far been lacking. In this work, we derive an equation for general memristor-inductor-resistor-capacitor (MEM-LRC) reservoirs that includes all network and dynamical constraints explicitly. Utilizing this we undertake a study of the computational capacity of these reservoirs. We demonstrate that hardware reservoirs may be constructed with extensive memory capacity and that the presence of memristors enacts a tradeoff between memory capacity and nonlinear computational capacity. Here, using these principles, we design reservoirs to tackle problems in signal processing, paving the way for applying hardware reservoirs to high-dimensional spatiotemporal systems.

• Research Organization: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
• Sponsoring Organization: USDOE Laboratory Directed Research and Development (LDRD) Program
• DOE Contract Number: 89233218CNA000001
• OSTI ID: 1995142
• Report Number(s): LA-UR-20-26991
• Journal Information: Proceedings of the Neuro-inspired Computational Elements Workshop, Journal Name: Proceedings of the Neuro-inspired Computational Elements Workshop
• Country of Publication: United States
• Language: English

Related Subjects

Circuits with memory
Memristors
Neuromorphic computing
Reservoir computing