RESUMO
Convolutions are one of the most critical signal and image processing operations. From spectral analysis to computer vision, convolutional filtering is often related to spatial information processing involving neighbourhood operations. As convolution operations are based around the product of two functions, vectors or matrices, dot products play a key role in the performance of such operations; for example, advanced image processing techniques require fast, dense matrix multiplications that typically take more than 90% of the computational capacity dedicated to solving convolutional neural networks. Silicon photonics has been demonstrated to be an ideal candidate to accelerate information processing involving parallel matrix multiplications. In this work, we experimentally demonstrate a multiwavelength approach with fully integrated modulators, tunable filters as microring resonator weight banks, and a balanced detector to perform matrix multiplications for image convolution operations. We develop a scattering matrix model that matches the experiment to simulate large-scale versions of these photonic systems with which we predict performance and physical constraints, including inter-channel cross-talk and bit resolution.
RESUMO
We propose and experimentally demonstrate an optical pulse sampling method for photonic blind source separation. The photonic system processes and separates wideband signals based on the statistical information of the mixed signals, and thus the sampling frequency can be orders of magnitude lower than the bandwidth of the signals. The ultra-fast optical pulses collect samples of the signals at very low sampling rates, and each sample is short enough to maintain the statistical properties of the signals. The low sampling frequency reduces the workloads of the analog to digital conversion and digital signal processing systems. In the meantime, the short pulse sampling maintains the accuracy of the sampled signals, so the statistical properties of the under-sampled signals are the same as the statistical properties of the original signals. The linear power range measurement shows that the sampling system with ultra-narrow optical pulse achieves a 30dB power dynamic range.
RESUMO
Recent progress in artificial intelligence is largely attributed to the rapid development of machine learning, especially in the algorithm and neural network models. However, it is the performance of the hardware, in particular the energy efficiency of a computing system that sets the fundamental limit of the capability of machine learning. Data-centric computing requires a revolution in hardware systems, since traditional digital computers based on transistors and the von Neumann architecture were not purposely designed for neuromorphic computing. A hardware platform based on emerging devices and new architecture is the hope for future computing with dramatically improved throughput and energy efficiency. Building such a system, nevertheless, faces a number of challenges, ranging from materials selection, device optimization, circuit fabrication and system integration, to name a few. The aim of this Roadmap is to present a snapshot of emerging hardware technologies that are potentially beneficial for machine learning, providing the Nanotechnology readers with a perspective of challenges and opportunities in this burgeoning field.
RESUMO
Integration of active electronics into photonic systems is necessary for large-scale photonic integration. While heterogeneous integration leverages high-performance electronics, a monolithic scheme can coexist by aiding the electronic processing, improving overall efficiency. We report a lateral bipolar junction transistor on a commercial silicon photonics foundry process. We achieved a DC current gain of 10 with a Darlington configuration, and using measured S-parameters for a single BJT, the available AC gain was at least 3dB for signal frequencies up to 1.1 GHz. Our single BJT demonstrated a transimpedance of 3.2mS/µm, which is about 70 times better than existing literature.
RESUMO
Independent component analysis (ICA) is a general-purpose technique for analyzing multi-dimensional data to reveal the underlying hidden factors that are maximally independent from each other. We report the first photonic ICA on mixtures of unknown signals by employing an on-chip microring (MRR) weight bank. The MRR weight bank performs so-called weighted addition (i.e., multiply-accumulate) operations on the received mixtures, and outputs a single reduced-dimensional representation of the signal of interest. We propose a novel ICA algorithm to recover independent components solely based on the statistical information of the weighted addition output, while remaining blind to not only the original sources but also the waveform information of the mixtures. We investigate both channel separability and near-far problems, and our two-channel photonic ICA experiment demonstrates our scheme holds comparable performance with the conventional software-based ICA method. Our numerical simulation validates the fidelity of the proposed approach, and studies noise effects to identify the operating regime of our method. The proposed technique could open new domains for future research in blind source separation, microwave photonics, and on-chip information processing.
RESUMO
We experimentally demonstrate all-optical reconfigurable nonlinear activation functions in a cavity-loaded Mach-Zehnder interferometer device on a silicon photonics platform, via the free-carrier dispersion effect. Our device is programmable to generate various nonlinear activation functions, including sigmoid, radial-basis, clamped rectified linear unit, and softplus, with tunable thresholds. We simulate benchmark tasks such as XOR and MNIST handwritten digit classifications with experimentally measured activation functions and obtain accuracies of 100% and 94%, respectively. Our device can serve as nonlinear units in photonic neural networks, while its nonlinear transfer function can be flexibly programmed to optimize the performance of different neuromorphic tasks.
RESUMO
We theoretically study the effect of free-carrier lifetime on processing speed and strength of nonlinearity, pertaining to our all-optical thresholder. We find that optimal device performance necessitates tuning lifetime while optimizing for both speed and nonlinearity. We also experimentally demonstrate device processing speed improvement from 400 Mbps to 2.5 Gbps by incorporating PN-junction mediated free-carrier lifetime tuning mechanism. Our study on the significance of free-carrier lifetime is universally applicable to any optical signal processing system reliant on silicon photonic nonlinearities.
RESUMO
Microwave communications have witnessed an incipient proliferation of multi-antenna and opportunistic technologies in the wake of an ever-growing demand for spectrum resources, while facing increasingly difficult network management over widespread channel interference and heterogeneous wireless broadcasting. Radio frequency (RF) blind source separation (BSS) is a powerful technique for demixing mixtures of unknown signals with minimal assumptions, but relies on frequency dependent RF electronics and prior knowledge of the target frequency band. We propose photonic BSS with unparalleled frequency agility supported by the tremendous bandwidths of photonic channels and devices. Specifically, our approach adopts an RF photonic front-end to process RF signals at various frequency bands within the same array of integrated microring resonators, and implements a novel two-step photonic BSS pipeline to reconstruct source identities from the reduced dimensional statistics of front-end output. We verify the feasibility and robustness of our approach by performing the first proof-of-concept photonic BSS experiments on mixed-over-the-air RF signals across multiple frequency bands. The proposed technique lays the groundwork for further research in interference cancellation, radio communications, and photonic information processing.
RESUMO
We propose and experimentally demonstrate an approach to generate and distribute secret keys over optical fiber communication infrastructure. Mach-Zehnder interferometers (MZIs) are adopted for key generation by transferring the environmental noise to random optical signals. A novel combination of wideband optical noise and an asymmetric MZI structure enables the secret keys to be securely transmitted and exchanged over public fiber links without being detected. We experimentally demonstrate this system and show reliable performance: keys are generated at the rate of 502 bit/s, and are successfully exchanged between two parties over a 10 km optical fiber with a bit error of â¼ 0.3%. System security analysis is performed by corroborating our experimental findings with simulations. The results show that our system can protect the key distribution under different attacks, attributed to wideband optical noise and asymmetric MZI structures. Compared to the previous schemes based on distributed MZIs, our scheme exploits localized MZI which provides twofold advantages. Firstly, the key generation rate can be increased by a factor of 5.7 at a negligible additional cost. Secondly, the system becomes robust to, in particular, active intrusion attack. The proposed system is a reliable and cost-effective solution for key establishment, and is compatible with the existing optical fiber communication infrastructure.
RESUMO
Photonic principal component analysis (PCA) enables high-performance dimensionality reduction in wideband analog systems. In this paper, we report a photonic PCA approach using an on-chip microring (MRR) weight bank to perform weighted addition operations on correlated wavelength-division multiplexed (WDM) inputs. We are able to configure the MRR weight bank with record-high accuracy and precision, and generate multi-channel correlated input signals in a controllable manner. We also consider the realistic scenario in which the PCA procedure remains blind to the waveforms of both the input signals and weighted addition output, and propose a novel PCA algorithm that is able to extract principal components (PCs) solely based on the statistical information of the weighted addition output. Our experimental demonstration of two-channel photonic PCA produces PCs holding consistently high correspondence to those computed by a conventional software-based PCA method. Our numerical simulation further validates that our scheme can be generalized to high-dimensional (up to but not limited to eight-channel) PCA with good convergence. The proposed technique could bring new solutions to problems in microwave communications, ultrafast control, and on-chip information processing.
RESUMO
Photonic neural networks benefit from both the high-channel capacity and the wave nature of light acting as an effective weighting mechanism through linear optics. Incorporating a nonlinear activation function by using active integrated photonic components allows neural networks with multiple layers to be built monolithically, eliminating the need for energy and latency costs due to external conversion. Interferometer-based modulators, while popular in communications, have been shown to require more area than absorption-based modulators, resulting in a reduced neural network density. Here, we develop a model for absorption modulators in an electro-optic fully connected neural network, including noise, and compare the network's performance with the activation functions produced intrinsically by five types of absorption modulators. Our results show the quantum well absorption modulator-based electro-optic neuron has the best performance allowing for 96% prediction accuracy with 1.7×10-12 J/MAC excluding laser power when performing MNIST classification in a 2 hidden layer feed-forward photonic neural network.
RESUMO
Microring weight banks present novel opportunities for reconfigurable, high-performance analog signal processing in photonics. Controlling microring filter response is a challenge due to fabrication variations and thermal sensitivity. Prior work showed continuous weight control of multiple wavelength-division multiplexed signals in a bank of microrings based on calibration and feedforward control. Other prior work has shown resonance locking based on feedback control by monitoring photoabsorption-induced changes in resistance across in-ring photoconductive heaters. In this work, we demonstrate continuous, multi-channel control of a microring weight bank with an effective 5.1 bits of accuracy on 2Gbps signals. Unlike resonance locking, the approach relies on an estimate of filter transmission versus photo-induced resistance changes. We introduce an estimate still capable of providing 4.2 bits of accuracy without any direct transmission measurements. Furthermore, we present a detailed characterization of this response for different values of carrier wavelength offset and power. Feedback weight control renders tractable the weight control problem in reconfigurable analog photonic networks.
RESUMO
Weighted addition is an elemental multi-input to single-output operation that can be implemented with high-performance photonic devices. Microring (MRR) weight banks bring programmable weighted addition to silicon photonics. Prior work showed that their channel limits are affected by coherent inter-channel effects that occur uniquely in weight banks. We fabricate two-pole designs that exploit this inter-channel interference in a way that is robust to dynamic tuning and fabrication variation. Scaling analysis predicts a channel count improvement of 3.4-fold, which is substantially greater than predicted by incoherent analysis used in conventional MRR devices. Advances in weight bank design expand the potential of reconfigurable analog photonic networks and multivariate microwave photonics.
RESUMO
Neocortical systems encode information in electrochemical spike timings, not just mean firing rates. Learning and memory in networks of spiking neurons is achieved by the precise timing of action potentials that induces synaptic strengthening (with excitation) or weakening (with inhibition). Inhibition should be incorporated into brain-inspired spike processing in the optical domain to enhance its information-processing capability. We demonstrate the simultaneous excitatory and inhibitory dynamics in an excitable (i.e., a pulsed) laser neuron, both numerically and experimentally. We investigate the bias strength effect, inhibitory strength effect, and excitatory and inhibitory input timing effect, based on the simulation platform of an integrated graphene excitable laser. We further corroborate these analyses with proof-of-principle experiments utilizing a fiber-based graphene excitable laser, where we introduce inhibition by directly modulating the gain of the laser. This technology may potentially open novel spike-processing functionality for future neuromorphic photonic systems.
Assuntos
Fenômenos Eletrofisiológicos/efeitos da radiação , Lasers , Modelos Neurológicos , Neocórtex/citologia , Neocórtex/fisiologia , Neocórtex/efeitos da radiação , Neurônios/citologia , Neurônios/efeitos da radiação , Fatores de TempoRESUMO
We demonstrate 4-channel, 2GHz weighted addition in a silicon microring filter bank. Accurate analog weight control becomes more difficult with increasing number of channels, N, as feedback approaches become impractical and brute force feedforward approaches take O(2N) calibration measurements in the presence of inter-channel dependence. We introduce model-based calibration techniques for thermal cross-talk and cross-gain saturation, which result in a scalable O(N) calibration routine and 3.8 bit feedforward weight accuracy on every channel. Practical calibration routines are indispensible for controlling large-scale microring systems. The effect of thermal model complexity on accuracy is discussed. Weighted addition based on silicon microrings can apply the strengths of photonic manufacturing, wideband information processing, and multiwavelength networks towards new paradigms of ultrafast analog distributed processing.
RESUMO
We propose an equivalent circuit model for photonic spike processing laser neurons with an embedded saturable absorbera simulation model for photonic excitable lasers (SIMPEL). We show that by mapping the laser neuron rate equations into a circuit model, SPICE analysis can be used as an efficient and accurate engine for numerical calculations, capable of generalization to a variety of different types of laser neurons with saturable absorber found in literature. The development of this model parallels the Hodgkin-Huxley model of neuron biophysics, a circuit framework which brought efficiency, modularity, and generalizability to the study of neural dynamics. We employ the model to study various signal-processing effects such as excitability with excitatory and inhibitory pulses, binary all-or-nothing response, and bistable dynamics.
RESUMO
We consider an optical technique for performing tunable weighted addition using wavelength-division multiplexed (WDM) inputs, the enabling function of a recently proposed photonic spike processing architecture [J. Lightwave Technol., 32 (2014)]. WDM weighted addition provides important advantages to performance, integrability, and networking capability that were not possible in any past approaches to optical neurocomputing. In this letter, we report a WDM weighted addition prototype used to find the first principal component of a 1Gbps, 8-channel signal. Wideband, multivariate techniques have immediate relevance to modern radio systems, and photonic spike processing networks enabled by WDM could open new domains of information processing that bring unprecedented bandwidth and intelligence to problems in radio communications, ultrafast control, and scientific computing.
RESUMO
The combination of ultrafast laser dynamics and dense on-chip multiwavelength networking could potentially address new domains of real-time signal processing that require both speed and complexity. We present a physically realistic optoelectronic simulation model of a circuit for dynamical laser neural networks and verify its behavior. We describe the physics, dynamics, and parasitics of one network node, which includes a bank of filters, a photodetector, and excitable laser. This unconventional circuit exhibits both cascadability and fan-in, critical properties for the large-scale networking of information processors based on laser excitability. In addition, it can be instantiated on a photonic integrated circuit platform and requires no off-chip optical I/O. Our proposed processing system could find use in emerging applications, including cognitive radio and low-latency control.
RESUMO
We propose and experimentally demonstrate a novel architecture for interfacing and transmitting a Gigabit Ethernet (GbE) signal using asynchronous incoherent optical code division multiple access (OCDMA). This is the first such asynchronous incoherent OCDMA system carrying GbE data being demonstrated to be working among multi-users where each user is operating with an independent clock/data rate and is granted random access to the network. Three major components, the GbE interface, the OCDMA transmitter, and the OCDMA receiver are discussed in detail. The performance of the system is studied and characterized through measuring eye diagrams, bit-error rate and packet loss rate in real-time file transfer. Our Letter also addresses the near-far problem and realizes asynchronous transmission and detection of signal.
RESUMO
A temporal phase mask encryption method is proposed and experimentally demonstrated to improve the security of the stealth channel in an optical steganography system. The stealth channel is protected in two levels. In the first level, the data is carried by amplified spontaneous emission (ASE) noise, which cannot be detected in either the time domain or spectral domain. In the second level, even if the eavesdropper suspects the existence of the stealth channel, each data bit is covered by a fast changing phase mask. The phase mask code is always combined with the wide band noise from ASE. Without knowing the right phase mask code to recover the stealth data, the eavesdropper can only receive the noise like signal with randomized phase.