scispace - formally typeset

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.

AbstractArtificial 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.

...read more

Citations
More filters

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.

778 citations


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.

746 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.

585 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.

412 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.

384 citations


References
More filters

Proceedings Article
03 Dec 2012
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

73,871 citations


Journal ArticleDOI
28 May 2015-Nature
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Abstract: Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

33,931 citations


Journal ArticleDOI
26 Feb 2015-Nature
TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Abstract: The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

15,690 citations


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

  • ...The computational resolution of ONNs is limited by practical non-idealities, including (1) thermal crosstalk between phase shifters in interferometers, (2) optical coupling drift, (3) the finite precision with which an optical phase can be set (16 bits in our case), (4) photodetection noise and (5) finite photodetection dynamic range (30 dB in our case)....

    [...]

  • ...(3) Once a neural network is trained, the architecture can be passive, and computation on the optical signals will be performed without additional energy input....

    [...]

  • ...We used four instances of the OIU to realize the following matrix transformations in the spatial-mode basis: (1) U((1))Σ((1)), (2) V((1)), (3) U((2))Σ((2)) and (4) V((2))....

    [...]

  • ...Transformations (1) and (2) realize the first matrix M((1)), and (3) and (4) implement M((2))....

    [...]


Journal ArticleDOI
28 Jul 2006-Science
Abstract: High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuning the weights in such "autoencoder" networks, but this works well only if the initial weights are close to a good solution. We describe an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data.

14,206 citations


Posted Content
Abstract: Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures. Caffe fits industry and internet-scale media needs by CUDA GPU computation, processing over 40 million images a day on a single K40 or Titan GPU ($\approx$ 2.5 ms per image). By separating model representation from actual implementation, Caffe allows experimentation and seamless switching among platforms for ease of development and deployment from prototyping machines to cloud environments. Caffe is maintained and developed by the Berkeley Vision and Learning Center (BVLC) with the help of an active community of contributors on GitHub. It powers ongoing research projects, large-scale industrial applications, and startup prototypes in vision, speech, and multimedia.

12,530 citations