2019/10/25 by Matthias Freiberger, Freiberger, Matthias, Peter Bienstman +3
Computer Science · Engineering · #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Signal Processing (eess.SP) #cs.ET #cs.LG #cs.NE #eess.SP #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1910.13332
Submitted to the IEEE International Conference on Rebooting Computing 2019; accepted as a poster, will not be presented though
arxiv created 2019/10/25 · arxiv updated 2019/10/30
Photonic reservoir computing is a promising candidate for low-energy computing at high bandwidths. Despite recent successes, there are bounds to what one can achieve simply by making photonic reservoirs larger. Therefore, a switch from single-reservoir computing to multi-reservoir and even deep physical reservoir computing is desirable. Given that backpropagation can not be used directly to train multi-reservoir systems in our targeted setting, we propose an alternative approach that still uses its power to derive intermediate targets. In this work we report our findings on a conducted experiment to evaluate the general feasibility of our approach by training a network of 3 Echo State Networks to perform the well-known NARMA-10 task using targets derived through backpropagation. Our results indicate that our proposed method is well-suited to train multi-reservoir systems in a efficient way.