Published In

Nanoscale Architectures (NANOARCH), 2015 IEEE/ACM International Symposium on

Document Type

Post-Print

Publication Date

7-2015

Subjects

Computer architecture -- Design, Memristors

Abstract

Advances in materials science have led to physical instantiations of self-assembled networks of memristive devices and demonstrations of their computational capability through reservoir computing. Reservoir computing is an approach that takes advantage of collective system dynamics for real-time computing. A dynamical system, called a reservoir, is excited with a time-varying signal and observations of its states are used to reconstruct a desired output signal. However, such a monolithic assembly limits the computational power due to signal interdependency and the resulting correlated readouts. Here, we introduce an approach that hierarchically composes a set of interconnected memristive networks into a larger reservoir. We use signal amplification and restoration to reduce reservoir state correlation, which improves the feature extraction from the input signals. Using the same number of output signals, such a hierarchical composition of heterogeneous small networks outperforms monolithic memristive networks by at least 20% on waveform generation tasks. On the NARMA-10 task, we reduce the error by up to a factor of 2 compared to homogeneous reservoirs with sigmoidal neurons, whereas single memristive networks are unable to produce the correct result. Hierarchical composition is key for solving more complex tasks with such novel nano-scale hardware.

Description

This paper appears in: Nanoscale Architectures (NANOARCH), 2015 IEEE/ACM International Symposium on 8-10 July 2015 Copyright 2015 IEEE.

DOI

10.1109/NANOARCH.2015.7180583

Persistent Identifier

http://archives.pdx.edu/ds/psu/16487

Share

COinS