Training Passive Photonic Reservoirs with Integrated Optical Readout
Loading...
Date
2018
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Abstract
As Moore’s law comes to an end, neuromorphic
approaches to computing are on the rise. One of these, passive
photonic reservoir computing, is a strong candidate for computing
at high bitrates (>10 Gbps) and with low energy consumption.
Currently though, both benefits are limited by the necessity
to perform training and readout operations in the electrical
domain. Thus, efforts are currently underway in the photonic
community to design an integrated optical readout, which allows
to perform all operations in the optical domain. In addition to
the technological challenge of designing such a readout, new
algorithms have to be designed in order to train it. Foremost,
suitable algorithms need to be able to deal with the fact that
the actual on-chip reservoir states are not directly observable.
In this work, we investigate several options for such a training
algorithm and propose a solution in which the complex states of
the reservoir can be observed by appropriately setting the readout
weights, while iterating over a predefined input sequence. We
perform numerical simulations in order to compare our method
with an ideal baseline requiring full observability as well as with
an established black-box optimization approach (CMA-ES).
Description
Keywords
Cognitive Computing, Reservoir Computing, Photonic Computing, Neuromorphic Computing, Nonlinearity Inversion, Integrated Optical Readout, Limited Observability
Citation
Freiberger, M., Katumba, A., Bienstman, P., & Dambre, J. (2018). Training passive photonic reservoirs with integrated optical readout. IEEE transactions on neural networks and learning systems , 30 (7), 1943-1953.