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
TL;DR: In this article, the authors demonstrate a photonic molecule with two distinct energy levels using coupled lithium niobate microring resonators and control it by external microwave excitation, using concepts of canonical two-level systems including Autler-Townes splitting, Stark shift, Rabi oscillation and Ramsey interference.
Abstract: Physical systems with discrete energy levels are ubiquitous in nature and are fundamental building blocks of quantum technology Realizing controllable artificial atom- and molecule-like systems for light would enable coherent and dynamic control of the frequency, amplitude and phase of photons1–5 In this work, we demonstrate a ‘photonic molecule’ with two distinct energy levels using coupled lithium niobate microring resonators and control it by external microwave excitation We show that the frequency and phase of light can be precisely controlled by programmed microwave signals, using concepts of canonical two-level systems including Autler–Townes splitting, Stark shift, Rabi oscillation and Ramsey interference Through such coherent control, we show on-demand optical storage and retrieval by reconfiguring the photonic molecule into a bright–dark mode pair These results of dynamic control of light in a programmable and scalable electro-optic system open doors to applications in microwave signal processing6, quantum photonic gates in the frequency domain7 and exploring concepts in optical computing8 and topological physics3,9 Coupled lithium niobate ring resonators enable control of a ‘photonic molecule’ by programmed microwave signals An on-demand optical storage and retrieval system is demonstrated
151 citations
TL;DR: In this paper, an optical neural chip (ONC) that implements truly complex-valued neural networks is presented, and the performance of the ONC is evaluated for simple Boolean tasks, species classification of an Iris dataset, classifying nonlinear datasets (Circle and Spiral), and handwriting recognition.
Abstract: Complex-valued neural networks have many advantages over their real-valued counterparts. Conventional digital electronic computing platforms are incapable of executing truly complex-valued representations and operations. In contrast, optical computing platforms that encode information in both phase and magnitude can execute complex arithmetic by optical interference, offering significantly enhanced computational speed and energy efficiency. However, to date, most demonstrations of optical neural networks still only utilize conventional real-valued frameworks that are designed for digital computers, forfeiting many of the advantages of optical computing such as efficient complex-valued operations. In this article, we highlight an optical neural chip (ONC) that implements truly complex-valued neural networks. We benchmark the performance of our complex-valued ONC in four settings: simple Boolean tasks, species classification of an Iris dataset, classifying nonlinear datasets (Circle and Spiral), and handwriting recognition. Strong learning capabilities (i.e., high accuracy, fast convergence and the capability to construct nonlinear decision boundaries) are achieved by our complex-valued ONC compared to its real-valued counterpart.
150 citations
TL;DR: An optical pulse-width modulation (PWM) switching of phase-change materials on an integrated waveguide is developed, which allows practical implementation of photonic memories and logic devices.
Abstract: Inspired by the great success of fiber optics in ultrafast data transmission, photonic computing is being extensively studied as an alternative to replace or hybridize electronic computers, which are reaching speed and bandwidth limitations. Mimicking and implementing basic computing elements on photonic devices is a first and essential step toward all-optical computers. Here, an optical pulse-width modulation (PWM) switching of phase-change materials on an integrated waveguide is developed, which allows practical implementation of photonic memories and logic devices. It is established that PWM with low peak power is very effective for recrystallization of phase-change materials, in terms of both energy efficiency and process control. Using this understanding, multilevel photonic memories with complete random accessibility are then implemented. Finally, programmable optical logic devices are demonstrated conceptually and experimentally, with logic "OR" and "NAND" achieved on just a single integrated photonic phase-change cell. This study provides a practical and elegant technique to optically program photonic phase-change devices for computing applications.
147 citations
University of Pavia1, University of Southampton2, Keio University3, Huazhong University of Science and Technology4, Peking University5, The Catholic University of America6, University of Notre Dame7, Malaviya National Institute of Technology, Jaipur8, University of Southern California9, King Saud University10, Chalmers University of Technology11, University of Strathclyde12, Sant'Anna School of Advanced Studies13, University of Twente14, University College London15, University of California, Santa Barbara16, École Polytechnique Fédérale de Lausanne17, University of Copenhagen18, University of Sydney19, Nippon Telegraph and Telephone20, National Institute of Informatics21, Max Planck Society22, University of Bath23
TL;DR: The Roadmap is organized so as to put side by side contributions on different aspects of optical processing, aiming to enhance the cross-contamination of ideas between scientists working in three different fields of photonics: optical gates and logical units, high bit-rate signal processing and optical quantum computing.
Abstract: The ability to process optical signals without passing into the electrical domain has always attracted the attention of the research community. Processing photons by photons unfolds new scenarios, in principle allowing for unseen signal processing and computing capabilities. Optical computation can be seen as a large scientific field in which researchers operate, trying to find solutions to their specific needs by different approaches; although the challenges can be substantially different, they are typically addressed using knowledge and technological platforms that are shared across the whole field. This significant know-how can also benefit other scientific communities, providing lateral solutions to their problems, as well as leading to novel applications. The aim of this Roadmap is to provide a broad view of the state-of-the-art in this lively scientific research field and to discuss the advances required to tackle emerging challenges, thanks to contributions authored by experts affiliated to both academic institutions and high-tech industries. The Roadmap is organized so as to put side by side contributions on different aspects of optical processing, aiming to enhance the cross-contamination of ideas between scientists working in three different fields of photonics: optical gates and logical units, high bit-rate signal processing and optical quantum computing. The ultimate intent of this paper is to provide guidance for young scientists as well as providing research-funding institutions and stake holders with a comprehensive overview of perspectives and opportunities offered by this research field.
142 citations
TL;DR: A broadband diffractive optical neural network design that simultaneously processes a continuum of wavelengths generated by a temporally incoherent broadband source to all-optically perform a specific task learned using deep learning is reported.
Abstract: Deep learning has been transformative in many fields, motivating the emergence of various optical computing architectures. Diffractive optical network is a recently introduced optical computing framework that merges wave optics with deep-learning methods to design optical neural networks. Diffraction-based all-optical object recognition systems, designed through this framework and fabricated by 3D printing, have been reported to recognize hand-written digits and fashion products, demonstrating all-optical inference and generalization to sub-classes of data. These previous diffractive approaches employed monochromatic coherent light as the illumination source. Here, we report a broadband diffractive optical neural network design that simultaneously processes a continuum of wavelengths generated by a temporally incoherent broadband source to all-optically perform a specific task learned using deep learning. We experimentally validated the success of this broadband diffractive neural network architecture by designing, fabricating and testing seven different multi-layer, diffractive optical systems that transform the optical wavefront generated by a broadband THz pulse to realize (1) a series of tuneable, single-passband and dual-passband spectral filters and (2) spatially controlled wavelength de-multiplexing. Merging the native or engineered dispersion of various material systems with a deep-learning-based design strategy, broadband diffractive neural networks help us engineer the light-matter interaction in 3D, diverging from intuitive and analytical design methods to create task-specific optical components that can all-optically perform deterministic tasks or statistical inference for optical machine learning.
139 citations
References
More filters
Proceedings Article•
03 Dec 2012TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which 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.
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.
73,978 citations
[...]
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.
46,982 citations
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.
23,074 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))....
[...]
TL;DR: In this article, 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 is described.
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.
16,717 citations
TL;DR: This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
14,635 citations
"Deep learning with coherent nanopho..." refers methods in this paper
...ANNs can be trained by feeding training data into the input layer and then computing the output by forward propagation; weighting parameters in each matrix are subsequently optimized using back propagation [16]....
[...]