Photonic Delay Systems as Machine Learning Implementations
This work addresses the challenge of improving machine learning implementations on analog hardware for researchers in photonics and neuromorphic computing, though it is incremental as it builds on existing gradient descent techniques.
The paper tackled the problem of extending the applicability of photonic delay systems beyond Reservoir Computing by optimizing input encodings using gradient descent with backpropagation through time, resulting in significantly better performance than the common approach.
Nonlinear photonic delay systems present interesting implementation platforms for machine learning models. They can be extremely fast, offer great degrees of parallelism and potentially consume far less power than digital processors. So far they have been successfully employed for signal processing using the Reservoir Computing paradigm. In this paper we show that their range of applicability can be greatly extended if we use gradient descent with backpropagation through time on a model of the system to optimize the input encoding of such systems. We perform physical experiments that demonstrate that the obtained input encodings work well in reality, and we show that optimized systems perform significantly better than the common Reservoir Computing approach. The results presented here demonstrate that common gradient descent techniques from machine learning may well be applicable on physical neuro-inspired analog computers.