#	Pagina
attuale pagina	/open-h2020/projects/198823/results.html

Report

Teaser, summary, work performed and final results

Periodic Reporting for period 2 - PHRESCO (PHotonic REServoir COmputing)

Teaser

Summary

The PHRESCO project focuses on the development of efficient cognitive computing into a specific silicon-based technology. PHRESCO will co-design a new reservoir computing chip, including innovative electronic and photonic components that will enable major breakthrough in the field. Figure 1 summarizes the PHRESCO concept. The consortium of the project is composed by the Katholieke Universiteit Leuven (KUL) in Belgium, who is the coordinator, the Universiteit Gent (UGent) in Belgium, the Leibniz Institute for Innovative Microelectronics (IHP) in Germany, IBM Research GmbH in Switzerland and the Centrale SupÃ©lec (CS) in France.

New computing paradigms are required to feed the next revolution in Information and Communication Technology (ICT). Machines that can learn, but also handle vast amount of data, need to be invented. In order to achieve this goal and still reduce the energy footprint of ICT, 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, but 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 on 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 components that will enable major breakthrough in the field.

We will i) scale optical RC systems 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.

Work performed

In the first phase of the Phresco project, a first generation reservoir with 18 nodes and integrated readout was designed and fabricated. The chip was designed as a 2 x 9 photonics swirl reservoir integrated with 3 readout technologies: a silicon readout, a vanadium oxide (VO2) readout and a barium titanate (BaTiO3) readout. The first set of prototype chips were produced and characterised by transmission experiments. The first end-to-end measurements of the reservoir states were attempted. Particle Swarm Optimization training method has been used to simulate the training of a 2x9 reservoir in order to establish a baseline, as well as a first fall-back training method for our prototypes. For a more efficient and fast training, a method based on the inversion of the output nonlinearity of the reservoir has been developed.

At the level of the individual components, the extension of the current functionalities of the new proposed materials was studied.Regarding the VO2 technology, optical and electro-optical characterization of VO2-Si photonic structures (1st generation of test chips) was done. However, it was not possible to stabilize a non-volatile switching of the Vo2 layers. On the other hand, the performance of BaTiO3 based programmable weights was studied. Electro-optical characterization of BaTiO3-Si devices confirmed the Pockels effect and the reversible and non-volatile switching behaviour of the BaTiO3 layers. An experimental platform has been designed and developed for characterization of non-linear behavior on BaTiO3 thin films. The test experiments show that polarized light can be coupled and detected before and after the sample respectively.

During the second phase of the Phresco project, the majority of the efforts were focused on the co-integration of different components on the photonic chips, i.e. weighting elements, amplifier and nonlinear elements. Regarding the weighting elements, we established a procedure to erase the history of a weight, independent of the previous settings. In the case of VO2, we have demonstrated a tunable transverse electric pass polarizer based on hybrid VO2/Si devices showing the potential of VO2 as an active material for opto-electronic devices.

In parallel, large efforts of the consortium was dedicated to the design of the second-generation chip. This part of the work included simulations to optimize the performance of components, architecture layout, best input strategy, best way to readout and combine the different states and power budget studies. The available prototype was upscaled to larger networks (60 nodes), with an on-chip readout and novel training approaches, and the scalability and cascadability of these RC networks were investigated. From the analysis of performance of the reservoir it could be concluded that a chaining architecture can be optimal in order to leverage the performance of electro-optical and fully optical passive photonic reservoir computing systems.

At the level of the individual components, we greatly progressed in the fabrication of III/V based amplifiers, which showed optical gain at wavelength 1300 nm, and could successfully couple light between Si-photonic structures and III/V devices placed at different photonic layers.Finally, we also examined the non-linearity properties in the BaTiO3 layer by using an experimental setup specifically designed for the study of the photorefractive effect.

Final results

The technologies that has matured the most during the first phase of the project, namely the photonic reservoir technology and the research focussing on barium titanate, will be described respectively focussing on their progression beyond the current state-of the-art.

On the level of photonic reservoir computing, the first generation prototype of Phresco goes beyond the state-of-the-art, since it will be the first realisation of a passive photonic reservoir with integrated all-optical readout. This will allow for high-speed low-power operation, since electro-optical conversions, analog-digital conversions and digital computations will no longer be needed to construct the output of the reservoir. To make this possible, also a novel training algorithm called non-linearity inversion was developed, which can deal with the incomplete observability of the reservoir states. All of this paves the way for larger reservoir which can tackle more complex problems.

On the material level, the integration of barium titanate with strong electro-optical properties and a confirmation of the Pockels effect in active structures is clearly beyond state-of-the-art. Previously, only passive waveguides or active waveguides with ambiguous switching behaviour have been demonstrated. Bringing a material with strong Pockels coefficients into the silicon photonic platform enhances the opportunities for designers to create novel photonic circuits that could rely on physical effects previously not available in silicon photonics. In particular, our demonstration of integrating this material on wafers processed in a standard CMOS production line shows the applicability and scalability of the new technology.