scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Deep learning with coherent nanophotonic circuits

01 Jul 2017-Vol. 11, Iss: 7, pp 441-446
TL;DR: A new architecture for a fully optical neural network is demonstrated that enables a computational speed enhancement of at least two orders of magnitude and three order of magnitude in power efficiency over state-of-the-art electronics.
Abstract: Artificial Neural Networks have dramatically improved performance for many machine learning tasks. We demonstrate a new architecture for a fully optical neural network that enables a computational speed enhancement of at least two orders of magnitude and three orders of magnitude in power efficiency over state-of-the-art electronics.
Citations
More filters
Journal ArticleDOI
TL;DR: This article reviews in a selective way the recent research on the interface between machine learning and the physical sciences, including conceptual developments in ML motivated by physical insights, applications of machine learning techniques to several domains in physics, and cross fertilization between the two fields.
Abstract: Machine learning (ML) encompasses a broad range of algorithms and modeling tools used for a vast array of data processing tasks, which has entered most scientific disciplines in recent years. This article reviews in a selective way the recent research on the interface between machine learning and the physical sciences. This includes conceptual developments in ML motivated by physical insights, applications of machine learning techniques to several domains in physics, and cross fertilization between the two fields. After giving a basic notion of machine learning methods and principles, examples are described of how statistical physics is used to understand methods in ML. This review then describes applications of ML methods in particle physics and cosmology, quantum many-body physics, quantum computing, and chemical and material physics. Research and development into novel computing architectures aimed at accelerating ML are also highlighted. Each of the sections describe recent successes as well as domain-specific methodology and challenges.

1,504 citations

Journal ArticleDOI
24 Sep 2018-Nature
TL;DR: Monolithically integrated lithium niobate electro-optic modulators that feature a CMOS-compatible drive voltage, support data rates up to 210 gigabits per second and show an on-chip optical loss of less than 0.5 decibels are demonstrated.
Abstract: Electro-optic modulators translate high-speed electronic signals into the optical domain and are critical components in modern telecommunication networks1,2 and microwave-photonic systems3,4. They are also expected to be building blocks for emerging applications such as quantum photonics5,6 and non-reciprocal optics7,8. All of these applications require chip-scale electro-optic modulators that operate at voltages compatible with complementary metal–oxide–semiconductor (CMOS) technology, have ultra-high electro-optic bandwidths and feature very low optical losses. Integrated modulator platforms based on materials such as silicon, indium phosphide or polymers have not yet been able to meet these requirements simultaneously because of the intrinsic limitations of the materials used. On the other hand, lithium niobate electro-optic modulators, the workhorse of the optoelectronic industry for decades9, have been challenging to integrate on-chip because of difficulties in microstructuring lithium niobate. The current generation of lithium niobate modulators are bulky, expensive, limited in bandwidth and require high drive voltages, and thus are unable to reach the full potential of the material. Here we overcome these limitations and demonstrate monolithically integrated lithium niobate electro-optic modulators that feature a CMOS-compatible drive voltage, support data rates up to 210 gigabits per second and show an on-chip optical loss of less than 0.5 decibels. We achieve this by engineering the microwave and photonic circuits to achieve high electro-optical efficiencies, ultra-low optical losses and group-velocity matching simultaneously. Our scalable modulator devices could provide cost-effective, low-power and ultra-high-speed solutions for next-generation optical communication networks and microwave photonic systems. Furthermore, our approach could lead to large-scale ultra-low-loss photonic circuits that are reconfigurable on a picosecond timescale, enabling a wide range of quantum and classical applications5,10,11 including feed-forward photonic quantum computation. Chip-scale lithium niobate electro-optic modulators that rapidly convert electrical to optical signals and use CMOS-compatible voltages could prove useful in optical communication networks, microwave photonic systems and photonic computation.

1,358 citations

Journal ArticleDOI
07 Sep 2018-Science
TL;DR: 3D-printed D2NNs are created that implement classification of images of handwritten digits and fashion products, as well as the function of an imaging lens at a terahertz spectrum.
Abstract: Deep learning has been transforming our ability to execute advanced inference tasks using computers. Here we introduce a physical mechanism to perform machine learning by demonstrating an all-optical diffractive deep neural network (D2NN) architecture that can implement various functions following the deep learning-based design of passive diffractive layers that work collectively. We created 3D-printed D2NNs that implement classification of images of handwritten digits and fashion products, as well as the function of an imaging lens at a terahertz spectrum. Our all-optical deep learning framework can perform, at the speed of light, various complex functions that computer-based neural networks can execute; will find applications in all-optical image analysis, feature detection, and object classification; and will also enable new camera designs and optical components that perform distinctive tasks using D2NNs.

1,145 citations

Journal ArticleDOI
08 May 2019-Nature
TL;DR: An optical version of a brain-inspired neurosynaptic system, using wavelength division multiplexing techniques, is presented that is capable of supervised and unsupervised learning.
Abstract: Software implementations of brain-inspired computing underlie many important computational tasks, from image processing to speech recognition, artificial intelligence and deep learning applications. Yet, unlike real neural tissue, traditional computing architectures physically separate the core computing functions of memory and processing, making fast, efficient and low-energy computing difficult to achieve. To overcome such limitations, an attractive alternative is to design hardware that mimics neurons and synapses. Such hardware, when connected in networks or neuromorphic systems, processes information in a way more analogous to brains. Here we present an all-optical version of such a neurosynaptic system, capable of supervised and unsupervised learning. We exploit wavelength division multiplexing techniques to implement a scalable circuit architecture for photonic neural networks, successfully demonstrating pattern recognition directly in the optical domain. Such photonic neurosynaptic networks promise access to the high speed and high bandwidth inherent to optical systems, thus enabling the direct processing of optical telecommunication and visual data. An optical version of a brain-inspired neurosynaptic system, using wavelength division multiplexing techniques, is presented that is capable of supervised and unsupervised learning.

862 citations

Journal ArticleDOI
TL;DR: A tandem neural network architecture is demonstrated that tolerates inconsistent training instances in inverse design of nanophotonic devices and provides a way to train large neural networks for the inverseDesign of complex photonic structures.
Abstract: Data inconsistency leads to a slow training process when deep neural networks are used for the inverse design of photonic devices, an issue that arises from the fundamental property of nonuniqueness in all inverse scattering problems. Here we show that by combining forward modeling and inverse design in a tandem architecture, one can overcome this fundamental issue, allowing deep neural networks to be effectively trained by data sets that contain nonunique electromagnetic scattering instances. This paves the way for using deep neural networks to design complex photonic structures that require large training data sets.

619 citations

References
More filters
Proceedings ArticleDOI
02 Jun 2009
TL;DR: Low loss silicon waveguides fabricated without silicon etching by selective oxidation are demonstrated, showing propagation losses of 0.3dB/cm, roughness of0.3 nm RMS, and 0.0002 dB loss for a 90deg bend with 20 mum bending radius.
Abstract: We demonstrate low loss silicon waveguides fabricated without silicon etching by selective oxidation. We show propagation losses of 0.3dB/cm (λ=1.55µm), roughness of 0.3nm RMS, and 0.0002dB loss for a 90° bend with 20µm bending radius.

162 citations


"Deep learning with coherent nanopho..." refers background in this paper

  • ...Linear transformations (and certain nonlinear transformations) can be performed at the speed of light and detected at rates exceeding 100 GHz [12] in photonic networks, and in some cases, with minimal power consumption [13]....

    [...]

Journal ArticleDOI
TL;DR: In this paper, the existence of optical bistability in a finite-size nonlinear bidimensional photonic crystal doped by a microcavity was demonstrated by a rigorous theory of diffraction.
Abstract: We numerically demonstrate the existence of optical bistability in a finite-size nonlinear bidimensional photonic crystal doped by a microcavity. The numerical results are obtained by a rigorous theory of diffraction. We provide a theoretical model allowing to predict and explain the bistability phenomena from the resonances of the structure.

108 citations

Journal ArticleDOI
TL;DR: A robust simulated annealing algorithm that does not require any knowledge of the problems structure is reported on, which improves the performance as well as the robustness and warrants for a global optimum which is robust against data and implementation uncertainties.
Abstract: Complex systems can be optimized to improve the performance with respect to desired functionalities. An optimized solution, however, can become suboptimal or even infeasible, when errors in implementation or input data are encountered. We report on a robust simulated annealing algorithm that does not require any knowledge of the problems structure. This is necessary in many engineering applications where solutions are often not explicitly known and have to be obtained by numerical simulations. While this nonconvex and global optimization method improves the performance as well as the robustness, it also warrants for a global optimum which is robust against data and implementation uncertainties. We demonstrate it on a polynomial optimization problem and on a high-dimensional and complex nanophotonic engineering problem and show significant improvements in efficiency as well as in actual optimality.

103 citations


"Deep learning with coherent nanopho..." refers methods in this paper

  • ...In such a case, robust simulated annealing algorithms [37] can be used to train ANN parameters which is error-tolerant, hence when encoded in the ONN, will have better performance....

    [...]

Journal ArticleDOI
TL;DR: In this paper, a differential equation is derived and used to calculate the dynamic response of a saturable absorber to an incident light pulse of high intensity and short duration, and the application of the theory in the design of a laser amplifier chain for pulse sharpening is indicated briefly.
Abstract: A differential equation is derived and used to calculate the dynamic response of a saturable absorber to an incident light pulse of high intensity and short duration. Particular reference is made to the use of the phthalocyanine dyes which have been employed for laser Q-switching. It is found that high-intensity pulses are transmitted with little distortion or attenuation, but those of intermediate intensity show some reduction in pulse width and a delay in reaching peak intensity, in addition to suffering some attenuation. For a ruby-laser-phthalocyanine-dye system these effects would be expected for nanosecond pulse widths and peak intensities in the region of 106 w cm-2. The application of the theory in the design of a laser amplifier chain for pulse sharpening is indicated briefly.

88 citations


"Deep learning with coherent nanopho..." refers background in this paper

  • ...assume a saturable absorber threshold of p ' 1 MW/cm2 – valid for many dyes, semiconductors, and graphene [21, 22]....

    [...]

  • ...Saturable absorption is modeled as [21] (Supplement Section 2),...

    [...]

Journal ArticleDOI
TL;DR: In this article, the in-plane optical absorption and free carrier absorption in graphene-on-silicon waveguides using a pump-probe measurement over microsecond timescales were investigated.
Abstract: We experimentally study the in-plane optical absorption and free carrier absorption (FCA) in graphene-on-silicon waveguides using a pump-probe measurement over microsecond timescales. The silicon waveguide is fabricated using complementary metal-oxide-semiconductor compatible processes, and directly covered by a graphene layer. Saturable absorption in the graphene is observed at the beginning of the pump pulse followed by an increase in absorption. The increase in absorption builds up over several microseconds, and is experimental evidence that free carriers generated by the pump absorption in graphene can transfer into silicon waveguides. The FCA in silicon waveguides eventually dominates the optical loss, which reaches ~9 dB, after several microseconds. All-optical modulations of the probe light are thus demonstrated. There is also a large thermally induced change in waveguide effective refractive index because of the optical absorption in the graphene.

85 citations


"Deep learning with coherent nanopho..." refers background in this paper

  • ...For example, graphene layers integrated on nanophotonic waveguides have already been demonstrated as saturable absorbers [35]....

    [...]