Fiber echo state network analogue for high-bandwidth dual-quadrature signal processing

Abstract

All-optical platforms for recurrent neural networks can offer higher computational speed and energy efficiency. To produce a major advance in comparison with currently available digital signal processing methods, the new system would need to have high bandwidth and operate both signal quadratures (power and phase). Here we propose a fiber echo state network analogue (FESNA)-the first optical technology that provides both high (beyond previous limits) bandwidth and dual-quadrature signal processing. We demonstrate applicability of the designed system for prediction tasks and for the mitigation of distortions in optical communication systems with multilevel dual-quadrature encoded signals.

Reservoir-Computing Based Equalization With Optical Pre-Processing for Short-Reach Optical Transmission

“…As shown in Fig. 8, however, a relatively low number of slices (16), already provides almost ideal compensation for distances approaching 20 km and less than 1 dB penalty for up to 35 km.…”

“…Alternatively to time-delayed schemes, in [13], [14], a linear passive reservoir with a second-order nonlinearity only at the output layer is used to equalize an OOK signal after fiber propagation by focusing on the impact of memory effect due to CD. Preliminary work on a nonlinear all-fiber optics implementation has also been proposed in [16]. The simulation results showed very promising performance improvements for equalization of quadrature amplitude modulated (QAM) signals affected by Kerr nonlinearity by using an RC scheme allowing processing both electrical field quadratures.…”

“…The simulation results showed very promising performance improvements for equalization of quadrature amplitude modulated (QAM) signals affected by Kerr nonlinearity by using an RC scheme allowing processing both electrical field quadratures. The results of [16] assume a static coherent transmission channel. As coherent transmission is inherently characterized by a fast time-varying channel, adaptive equalization is required to track effects such as polarization rotations.…”

“…Losing the information carried by the field's phase makes chromatic dispersion (CD) the major obstacle to extending the transmission reach. Several techniques are available for compensating for the intersymbol interference (ISI) induced by CD, by acting in the optical domain [2], [3], in the digital/electric domain [4], [5], [6], [7], [8], [9], [10], [11], [12] or by considering a joint optoelectronic approach [13], [14], [15], [16], [17], [18], [20]. Optical dispersion compensation techniques mainly rely on negative dispersion media, such as dispersion-compensating fibers (DCFs) or fiber Bragg gratings (FBGs).…”

Optimization Algorithms of Neural Networks for Traditional Time-Domain Equalizer in Optical Communications

“…NN-based equalizers for indoor optical wireless communications [8], 170 Mb/s visible light communications system [9] and modulation format identification in heterogeneous fiber-optic networks were proposed [10]. As a promising type of recurrent neural network, reservoir computing in all-optical implementation enables high-speed signal processing and can set the framework for a new generation of hardware for computing and future optical networks [11].…”