Abstract
Machine learning techniques have proven very efficient in assorted classification tasks. Nevertheless, processing time-dependent high-speed signals can turn into an extremely challenging task, especially when these signals have been nonlinearly distorted. Recently, analogue hardware concepts using nonlinear transient responses have been gaining significant interest for fast information processing. Here, we introduce a simplified photonic reservoir computing scheme for data classification of severely distorted optical communication signals after extended fibre transmission. To this end, we convert the direct bit detection process into a pattern recognition problem. Using an experimental implementation of our photonic reservoir computer, we demonstrate an improvement in bit-error-rate by two orders of magnitude, compared to directly classifying the transmitted signal. This improvement corresponds to an extension of the communication range by over 75%. While we do not yet reach full real-time post-processing at telecom rates, we discuss how future designs might close the gap.
Highlights
Recent developments in neuro-inspired information processing using recurrent neural networks (RNNs), cognitive computing approaches, machine learning techniques and deep learning[1,2] architectures have had a major impact on solving classification and pattern recognition tasks with remarkable efficiency[3,4,5,6,7]
We introduce a simplified reservoir computing (RC) approach with a sequential data processing architecture that allows for a high-speed hardware implementation
The concept we demonstrate here is generic and powerful and it can be applied to signals that may originate from any optical communication system configurations
Summary
Recent developments in neuro-inspired information processing using recurrent neural networks (RNNs), cognitive computing approaches, machine learning techniques and deep learning[1,2] architectures have had a major impact on solving classification and pattern recognition tasks with remarkable efficiency[3,4,5,6,7]. The current DSP methods are efficient as long as nonlinear signal distortions do not become too complicated For this reason, optimal designs of various transmission systems dictate that the launched optical power in standard single mode fibres (SSMF) should be always restricted to moderate levels (around or below 1 mW). Its role is to nonlinearly transform the input and, at the same time, to generate a mapping of the input onto a high-dimensional state space It was shown[13] that a single nonlinear element with time-delayed feedback can emulate a recurrent network by defining multiple nodes within the feedback loop with delay time τ. If we followed the original approach, we would need to inject these data vectors into the delay reservoir after multiplying them with the random connectivity matrix This represents a significant complication when implementing the scheme in hardware and at high speeds. The importance of selecting these values will be discussed in detail in the results section
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
