Reservoir Computing with Neuromorphic Hardware

We have a PhD studentship available in the Department of Electronic Engineering (EE) at York, starting in October 2021, to work on aspects of next-generation computing architectures and platforms based on the Reservoir Computing (RC) model. RC is derived from recurrent neural network theory exploiting non-linear dynamics of physical substrates for computation. Substrates include novel nano materials, neuromorphic hardware and analogue electronics.

Classical digital computing is power hungry, fragile, and hard to interface to the real world. Reservoir computing (RC) can help overcome these issues, particularly by being able to perform embodied computation that can directly exploit the natural dynamics of the substrate, thereby dramatically reducing power requirements and providing a natural fit to certain computational tasks. Introduced more than a decade ago, RC has proven to be an efficient approach for signal processing and dynamical pattern recognition, and state-of-the-art performance has been demonstrated in both simulation and physical implementation.

This PhD research project will help take RC to the next level: designing, building, applying and analysing complete, efficient and feasible RC architectures: a networked “reservoir of reservoirs” (RoR) platform.

You will create a flexible architecture based on underlying theory previously developed in the research group to support efficient, flexible and feasible multi-reservoir computers. Depending on your skillset you will develop a flexible RC platform focussing on reconfigurable programmable analogue electronics and substrate simulation. You will demonstrate your approach on a range of applications, starting from a smart microphone implementing noise cancelling, sound source isolation and speaker identification, and building up to a universal “edge processor” that can process data from diverse sensors (different timescales and modalities), trainable for different tasks and contexts.

This PhD project will run in the context of the EPSRC-funded MARCH (Magnetic Architectures for Reservoir Computing Hardware) project, involving the Universities of York and Sheffield, and will complement the research being performed there. A further related PhD studentship is available at York in CS https://www.findaphd.com/phds/project/reservoir-computing/?p129468.

For more information on the studentship, please contact Dr Martin Trefzer martin.trefzer@york.ac.uk

Entry requirements:

Candidates must have (or expect to obtain) a minimum of a UK upper second class honours degree (2.1) or equivalent in Electronic and Electrical Engineering, Physics, Computer Science, Mathematics or a related subject.

How to apply:

Applicants must apply via the University’s online application system at https://www.york.ac.uk/study/postgraduate-research/apply/. Please read the application guidance first so that you understand the various steps in the application process. To apply, please select the PhD in Electronic Engineering for October 2021 entry. Please specify in your PhD application that you would like to be considered for this studentship.