Leadership in enabling and industrial technologies - ICT - PHRESCO

New computing paradigms are required to feed the next revolution in Information Technology. Machines need to be invented that can learn, but also handle vast amount of data. In order to achieve this goal and still reduce the energy footprint of Information and Communication Technology, fundamental hardware innovations must be done. A physical implementation natively supporting new computing methods is required. Most of the time, CMOS is used to emulate e.g. neuronal behavior, and is intrinsically limited in power efficiency and speed.

Reservoir computing (RC) is one of the concepts that has proven its efficiency to perform tasks where traditional approaches fail. It is also one of the rare concepts of an efficient hardware realization of cognitive computing into a specific, silicon-based technology. Small RC systems have been demonstrated using optical fibers and bulk components. In 2014, optical RC networks based integrated photonic circuits were demonstrated. The PHRESCO project aims to bring photonic reservoir computing to the next level of maturity. A new RC chip will be co-designed, including innovative electronic and photonic component that will enable major breakthrough in the field. We will i) Scale optical RC systems up to 60 nodes ii) build an all-optical chip based on the unique electro-optical properties of new materials iii) Implement new learning algorithms to exploit the capabilities of the RC chip.

The hardware integration of beyond state-of-the-art components with novel system and algorithm design will pave the way towards a new era of optical, cognitive systems capable of handling huge amount of data at ultra-low power consumption.

Objectives

These are the objectives of PHRESCO:

• Objective 1: Extending the silicon photonic platform with novel materials and components to enable larger and more powerful photonic reservoirs. We will focus on functional oxides, in particular VO2 and BaTiO3, to obtain optical weighting elements, nonlinear optical components, and optical amplifiers.
• Objective 2: Design of larger PhRC systems (60 nodes, a factor of 4 larger than previously fabricated) and new training algorithms which only have access to a single observable.
• Objective 3: Demonstration of a working, large photonic reservoir computing chip on which a computational task is performed such as the recognition of an 8 bits pattern at 32 Gbit/s. In addition, also cascading of multiple, small-scale optical reservoirs will be demonstrated.
• Objective 4: Definition of an exploitation strategy to apply the novel PhRC systems to real world problems from a scientific, technological, and business point of view. Stability of the components, scalability, power-consumption, benchmarks with alternative computational approaches, costs, and potential market sizes will be thoroughly analyzed.

Role of Ghent University

Ghent University contributes to the project in three ways:

• Performing architectural studies in simulation to evaluate and compare different technological alternatives
• Designing and measuring prototypes (in collaboration with other partners)
• Developing optimization techniques (@design time) and online tuning techniques (@run time) based on machine learning

Contact

Prof. Joni Dambre
Department Electronics and Information Systems (ELIS - EA06)
Phone number: +32-9-264 34 09
E-mail: Joni.Dambre@Ugent.be

Prof. Peter Bienstman
Department of Information Technology (INTEC – EA05)
Phone number: +32-9-264 34 46
E-mail: Peter.Bienstman@Ugent.be