Reservoir Computing Hardware with Cellular Automata
This work provides a low-cost method for fast pattern recognition digital circuits, which is incremental as it builds on existing RC and ECA approaches.
The authors tackled the problem of implementing Reservoir Computing (RC) systems for pattern recognition by exhaustively testing Elementary Cellular Automata (ECA) rules and selecting rule 90 for hardware design, achieving competitive results on the MNIST database with improved processing time, circuit area, and power dissipation.
Elementary cellular automata (ECA) is a widely studied one-dimensional processing methodology where the successive iteration of the automaton may lead to the recreation of a rich pattern dynamic. Recently, cellular automata have been proposed as a feasible way to implement Reservoir Computing (RC) systems in which the automata rule is fixed and the training is performed using a linear regression. In this work we perform an exhaustive study of the performance of the different ECA rules when applied to pattern recognition of time-independent input signals using a RC scheme. Once the different ECA rules have been tested, the most accurate one (rule 90) is selected to implement a digital circuit. Rule 90 is easily reproduced using a reduced set of XOR gates and shift-registers, thus representing a high-performance alternative for RC hardware implementation in terms of processing time, circuit area, power dissipation and system accuracy. The model (both in software and its hardware implementation) has been tested using a pattern recognition task of handwritten numbers (the MNIST database) for which we obtained competitive results in terms of accuracy, speed and power dissipation. The proposed model can be considered to be a low-cost method to implement fast pattern recognition digital circuits.