Reservoir Computing in Lithium Niobate on Insulator Platforms

This work concerns time-delay reservoir computing (TDRC) in integrated photonic platforms, specifically the Lithium Niobate on Insulator (LNOI) platform. We propose a novel all-optical integrated architecture, which has only one tunable parameter in the form of a phase-shifter, and which can achieve good performance on several reservoir computing benchmark tasks. We also investigate the design space of this architecture and the asynchronous operation, which represents a departure from the more common framework of envisioning time-delay reservoir computers as networks in the stricter sense. Additionally, we propose to leverage the optical feedback to dispense with the input mask, which allows the bypassing of an O/E/O conversion, which is often necessary to apply the mask. In future work, this can allow the processing of real-time incoming signals, possibly for telecom/edge applications. The effects of the output electronic readout on the proposed architecture's performance are also investigated. Initial experimental work is also reported. The unifying theme of this work is to investigate the performance possibilities with minimum photonic hardware requirements, relying mainly on LNOI’s low losses which enables the integration of the feedback waveguide, and using only interference and subsequent intensity conversion (through a photodetector) as the nonlinearity. This provides a base for future work to compare against in terms of performance gains when additional nonlinearities are considered (such as those available on the LNOI platform), and when overall system complexity is increased by means of introducing more tunable parameters. Thus, the scope of this work is about the exploration of one particular unconventional computing approach (reservoir computing), using one particular technology (photonics), on one particular platform (lithium niobate on insulator). This work builds on the increasing interest of exploring unconventional computing, since it has been shown over the years that digital computers can no longer be a `one-size-fits-all', especially for emerging applications like artificial intelligence (AI). The future landscape of computing will likely encompass a rich variety of computing paradigms, architectures, and hardware, to meet the needs of rising specialized applications, and all in coexistence with digital computers which remain, at least for now, better suited for general-purpose computing.