Symmetry-Aware Reservoir Computing

Wendson A. S. Barbosa, Aaron Griffith, Graham E. Rowlands, Luke C. G. Govia, Guilhem J. Ribeill, Minh-Hai Nguyen, Thomas A. Ohki, Daniel J. Gauthier

We demonstrate that matching the symmetry properties of a reservoir computer (RC) to the data being processed can dramatically increase its processing power. We apply our method to the parity task, a challenging benchmark problem, which highlights the benefits of symmetry matching. Our method outperforms all other approaches on this task, even artificial neural networks (ANN) hand crafted for this problem. The symmetry-aware RC can obtain zero error using an exponentially reduced number of artificial neurons and training data, greatly speeding up the time-to-result. We anticipate that generalizations of our procedure will have widespread applicability in information processing with ANNs.

Knowledge Graph



Sign up or login to leave a comment