Constructing optimized binary masks for reservoir computing with delay systems
Open Access
- 10 January 2014
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 4 (1) , 3629
Abstract
Reservoir computing is a novel bio-inspired computing method, capable of solving complex tasks in a computationally efficient way. It has recently been successfully implemented using delayed feedback systems, allowing to reduce the hardware complexity of brain-inspired computers drastically. In this approach, the pre-processing procedure relies on the definition of a temporal mask which serves as a scaled time-mutiplexing of the input. Originally, random masks had been chosen, motivated by the random connectivity in reservoirs. This random generation can sometimes fail. Moreover, for hardware implementations random generation is not ideal due to its complexity and the requirement for trial and error. We outline a procedure to reliably construct an optimal mask pattern in terms of multipurpose performance, derived from the concept of maximum length sequences. Not only does this ensure the creation of the shortest possible mask that leads to maximum variability in the reservoir states for the given reservoir, it also allows for an interpretation of the statistical significance of the provided training samples for the task at hand.Keywords
This publication has 12 references indexed in Scilit:
- Parallel photonic information processing at gigabyte per second data rates using transient statesNature Communications, 2013
- Information Processing Capacity of Dynamical SystemsScientific Reports, 2012
- Optoelectronic Reservoir ComputingScientific Reports, 2012
- Information processing using a single dynamical node as complex systemNature Communications, 2011
- An experimental unification of reservoir computing methodsNeural Networks, 2007
- Backpropagation-decorrelation: online recurrent learning with O(N) complexity2005
- Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless CommunicationScience, 2004
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on PerturbationsNeural Computation, 2002
- New results on recurrent network training: unifying the algorithms and accelerating convergenceIEEE Transactions on Neural Networks, 2000
- Oscillation and Chaos in Physiological Control SystemsScience, 1977