Deep Photonic Reservoir Computer for Speech Recognition.

Speech recognition is a critical task in the field of artificial intelligence (AI) and has witnessed remarkable advancements thanks to large and complex neural networks, whose training process typically requires massive amounts of labeled data and computationally intensive operations. An alternative paradigm, reservoir computing (RC), is energy efficient and is well adapted to implementation in physical substrates, but exhibits limitations in performance when compared with more resource-intensive machine learning algorithms. In this work, we address this challenge by investigating different architectures of interconnected reservoirs, all falling under the umbrella of deep RC (DRC). We propose a photonic-based deep reservoir computer and evaluate its effectiveness on different speech recognition tasks. We show specific design choices that aim to simplify the practical implementation of a reservoir computer while simultaneously achieving high-speed processing of high-dimensional audio signals. Overall, with the present work, we hope to help the advancement of low-power and high-performance neuromorphic hardware.

Integrated programmable spectral filter for frequency-multiplexed neuromorphic computers.

Artificial neural networks (ANN) are a groundbreaking technology massively employed in a plethora of fields. Currently, ANNs are mostly implemented through electronic digital computers, but analog photonic implementations are very interesting mainly because of low power consumption and high bandwidth. We recently demonstrated a photonic neuromorphic computing system based on frequency multiplexing that executes ANNs algorithms as reservoir computing and Extreme Learning Machines. Neuron signals are encoded in the amplitude of the lines of a frequency comb, and neuron interconnections are realized through frequency-domain interference. Here we present an integrated programmable spectral filter designed to manipulate the optical frequency comb in our frequency multiplexing neuromorphic computing platform. The programmable filter controls the attenuation of 16 independent wavelength channels with a 20 GHz spacing. We discuss the design and the results of the chip characterization, and we preliminary demonstrate, through a numerical simulation, that the produced chip is suitable for the envisioned neuromorphic computing application.

High speed human action recognition using a photonic reservoir computer.

The recognition of human actions in videos is one of the most active research fields in computer vision. The canonical approach consists in a more or less complex preprocessing stages of the raw video data, followed by a relatively simple classification algorithm. Here we address recognition of human actions using the reservoir computing algorithm, which allows us to focus on the classifier stage. We introduce a new training method for the reservoir computer, based on "Timesteps Of Interest", which combines in a simple way short and long time scales. We study the performance of this algorithm using both numerical simulations and a photonic implementation based on a single non-linear node and a delay line on the well known KTH dataset. We solve the task with high accuracy and speed, to the point of allowing for processing multiple video streams in real time. The present work is thus an important step towards developing efficient dedicated hardware for video processing.

Photonic reservoir computer based on frequency multiplexing.

Reservoir computing is a brain-inspired approach for information processing, well suited to analog implementations. We report a photonic implementation of a reservoir computer that exploits frequency domain multiplexing to encode neuron states. The system processes 25 comb lines simultaneously (i.e., 25 neurons), at a rate of 20 MHz. We illustrate performances on two standard benchmark tasks: channel equalization and time series forecasting. We also demonstrate that frequency multiplexing allows output weights to be implemented in the optical domain, through optical attenuation. We discuss the perspectives for high-speed, high-performance, low-footprint implementations.

Photonic extreme learning machine based on frequency multiplexing.

The optical domain is a promising field for the physical implementation of neural networks, due to the speed and parallelism of optics. Extreme learning machines (ELMs) are feed-forward neural networks in which only output weights are trained, while internal connections are randomly selected and left untrained. Here we report on a photonic ELM based on a frequency-multiplexed fiber setup. Multiplication by output weights can be performed either offline on a computer or optically by a programmable spectral filter. We present both numerical simulations and experimental results on classification tasks and a nonlinear channel equalization task.

Photonic Reservoir Computer with Output Expansion for Unsupervized Parameter Drift Compensation.

We present a method to improve the performance of a reservoir computer by keeping the reservoir fixed and increasing the number of output neurons. The additional neurons are nonlinear functions, typically chosen randomly, of the reservoir neurons. We demonstrate the interest of this expanded output layer on an experimental opto-electronic system subject to slow parameter drift which results in loss of performance. We can partially recover the lost performance by using the output layer expansion. The proposed scheme allows for a trade-off between performance gains and system complexity.

Resource efficient single photon source based on active frequency multiplexing.

We propose a new, to the best of our knowledge, single photon source based on the principle of active multiplexing of heralded single photons, which, unlike previously reported architecture, requires a limited amount of physical resources. We discuss both its feasibility and the purity and indistinguishability of single photons as a function of the key parameters of a possible implementation.

Using a reservoir computer to learn chaotic attractors, with applications to chaos synchronization and cryptography.

Using the machine learning approach known as reservoir computing, it is possible to train one dynamical system to emulate another. We show that such trained reservoir computers reproduce the properties of the attractor of the chaotic system sufficiently well to exhibit chaos synchronization. That is, the trained reservoir computer, weakly driven by the chaotic system, will synchronize with the chaotic system. Conversely, the chaotic system, weakly driven by a trained reservoir computer, will synchronize with the reservoir computer. We illustrate this behavior on the Mackey-Glass and Lorenz systems. We then show that trained reservoir computers can be used to crack chaos based cryptography and illustrate this on a chaos cryptosystem based on the Mackey-Glass system. We conclude by discussing why reservoir computers are so good at emulating chaotic systems.

Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalization.

Reservoir computing is a bioinspired computing paradigm for processing time-dependent signals. The performance of its analog implementation is comparable to other state-of-the-art algorithms for tasks such as speech recognition or chaotic time series prediction, but these are often constrained by the offline training methods commonly employed. Here, we investigated the online learning approach by training an optoelectronic reservoir computer using a simple gradient descent algorithm, programmed on a field-programmable gate array chip. Our system was applied to wireless communications, a quickly growing domain with an increasing demand for fast analog devices to equalize the nonlinear distorted channels. We report error rates up to two orders of magnitude lower than previous implementations on this task. We show that our system is particularly well suited for realistic channel equalization by testing it on a drifting and a switching channel and obtaining good performances.

Embodiment of Learning in Electro-Optical Signal Processors.

Delay-coupled electro-optical systems have received much attention for their dynamical properties and their potential use in signal processing. In particular, it has recently been demonstrated, using the artificial intelligence algorithm known as reservoir computing, that photonic implementations of such systems solve complex tasks such as speech recognition. Here, we show how the backpropagation algorithm can be physically implemented on the same electro-optical delay-coupled architecture used for computation with only minor changes to the original design. We find that, compared to when the backpropagation algorithm is not used, the error rate of the resulting computing device, evaluated on three benchmark tasks, decreases considerably. This demonstrates that electro-optical analog computers can embody a large part of their own training process, allowing them to be applied to new, more difficult tasks.

Measuring the nonlinear refractive index of graphene using the optical Kerr effect method.

By means of the ultrafast optical Kerr effect method coupled to optical heterodyne detection (OHD-OKE), we characterize the third-order nonlinear response of graphene and compare it to experimental values obtained by the Z-scan method on the same samples. From these measurements, we estimate a negative nonlinear refractive index for monolayer graphene, n2=-1.1×10-13 m2/W. This is in contradiction to previously reported values, which leads us to compare our experimental measurements obtained by the OHD-OKE and the Z-scan method with theoretical and experimental values found in the literature and to discuss the discrepancies, taking into account parameters such as doping.

Fully analogue photonic reservoir computer.

Introduced a decade ago, reservoir computing is an efficient approach for signal processing. State of the art capabilities have already been demonstrated with both computer simulations and physical implementations. If photonic reservoir computing appears to be promising a solution for ultrafast nontrivial computing, all the implementations presented up to now require digital pre or post processing, which prevents them from exploiting their full potential, in particular in terms of processing speed. We address here the possibility to get rid simultaneously of both digital pre and post processing. The standalone fully analogue reservoir computer resulting from our endeavour is compared to previous experiments and only exhibits rather limited degradation of performances. Our experiment constitutes a proof of concept for standalone physical reservoir computers.

All-optical reservoir computer based on saturation of absorption.

Reservoir computing is a new bio-inspired computation paradigm. It exploits a dynamical system driven by a time-dependent input to carry out computation. For efficient information processing, only a few parameters of the reservoir needs to be tuned, which makes it a promising framework for hardware implementation. Recently, electronic, opto-electronic and all-optical experimental reservoir computers were reported. In those implementations, the nonlinear response of the reservoir is provided by active devices such as optoelectronic modulators or optical amplifiers. By contrast, we propose here the first reservoir computer based on a fully passive nonlinearity, namely the saturable absorption of a semiconductor mirror. Our experimental setup constitutes an important step towards the development of ultrafast low-consumption analog computers.

Supercontinuum generation in hydrogenated amorphous silicon waveguides at telecommunication wavelengths.

We report supercontinuum (SC) generation centered on the telecommunication C-band (1550 nm) in CMOS compatible hydrogenated amorphous silicon waveguides. A broadening of more than 550 nm is obtained in 1cm long waveguides of different widths using as pump picosecond pulses with on chip peak power as low as 4 W.

Secure and robust transmission and verification of unknown quantum states in Minkowski space.

An important class of cryptographic applications of relativistic quantum information work as follows. B generates a random qudit and supplies it to A at point P. A is supposed to transmit it at near light speed c to to one of a number of possible pairwise spacelike separated points Q1, …, Qn. A's transmission is supposed to be secure, in the sense that B cannot tell in advance which Qj will be chosen. This poses significant practical challenges, since secure reliable long-range transmission of quantum data at speeds near to c is presently not easy. Here we propose different techniques to overcome these diffculties. We introduce protocols that allow secure long-range implementations even when both parties control only widely separated laboratories of small size. In particular we introduce a protocol in which A needs send the qudit only over a short distance, and securely transmits classical information (for instance using a one time pad) over the remaining distance. We further show that by using parallel implementations of the protocols security can be maintained in the presence of moderate amounts of losses and errors.

Silicon-on-insulator integrated source of polarization-entangled photons.

We report the experimental generation of polarization-entangled photons at telecommunication wavelengths using spontaneous four-wave mixing in silicon-on-insulator wire waveguides. The key component is a 2D coupler that transforms path entanglement into polarization entanglement at the output of the device. Using quantum state tomography we find that the produced state has fidelity 88% with a pure nonmaximally entangled state. The produced state violates the CHSH Bell inequality by S=2.37 ± 0.19.

Mean-field theory of echo state networks.

Dynamical systems driven by strong external signals are ubiquitous in nature and engineering. Here we study "echo state networks," networks of a large number of randomly connected nodes, which represent a simple model of a neural network, and have important applications in machine learning. We develop a mean-field theory of echo state networks. The dynamics of the network is captured by the evolution law, similar to a logistic map, for a single collective variable. When the network is driven by many independent external signals, this collective variable reaches a steady state. But when the network is driven by a single external signal, the collective variable is non stationary but can be characterized by its time averaged distribution. The predictions of the mean-field theory, including the value of the largest Lyapunov exponent, are compared with the numerical integration of the equations of motion.

All-optical reservoir computing.

Reservoir Computing is a novel computing paradigm that uses a nonlinear recurrent dynamical system to carry out information processing. Recent electronic and optoelectronic Reservoir Computers based on an architecture with a single nonlinear node and a delay loop have shown performance on standardized tasks comparable to state-of-the-art digital implementations. Here we report an all-optical implementation of a Reservoir Computer, made of off-the-shelf components for optical telecommunications. It uses the saturation of a semiconductor optical amplifier as nonlinearity. The present work shows that, within the Reservoir Computing paradigm, all-optical computing with state-of-the-art performance is possible.

Information processing capacity of dynamical systems.

Many dynamical systems, both natural and artificial, are stimulated by time dependent external signals, somehow processing the information contained therein. We demonstrate how to quantify the different modes in which information can be processed by such systems and combine them to define the computational capacity of a dynamical system. This is bounded by the number of linearly independent state variables of the dynamical system, equaling it if the system obeys the fading memory condition. It can be interpreted as the total number of linearly independent functions of its stimuli the system can compute. Our theory combines concepts from machine learning (reservoir computing), system modeling, stochastic processes, and functional analysis. We illustrate our theory by numerical simulations for the logistic map, a recurrent neural network, and a two-dimensional reaction diffusion system, uncovering universal trade-offs between the non-linearity of the computation and the system's short-term memory.

Z-scan measurement of the nonlinear refractive index of graphene.

Under strong laser illumination, few-layer graphene exhibits both a transmittance increase due to saturable absorption and a nonlinear phase shift. Here, we unambiguously distinguish these two nonlinear optical effects and identify both real and imaginary parts of the complex nonlinear refractive index of graphene. We show that graphene possesses a giant nonlinear refractive index n(2)≃10(-7) cm(2) W(-1), almost 9 orders of magnitude larger than bulk dielectrics. We find that the nonlinear refractive index decreases with increasing excitation flux but slower than the absorption. This suggests that graphene may be a very promising nonlinear medium, paving the way for graphene-based nonlinear photonics.