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: In this article , the applications of graphene oxide to nonlinear integrated photonic devices are reviewed, followed by comparisons of the nonlinear optical performance of different integrated platforms incorporating GO as well as hybrid integrated devices including different kinds of 2D materials.
Abstract: Integrated photonic devices operating via optical nonlinearities offer a powerful solution for all‐optical information processing, yielding processing speeds that are well beyond that of electronic processing as well as providing the added benefits of compact footprint, high stability, high scalability, and small power consumption. The increasing demand for high‐performance nonlinear integrated photonic devices has facilitated the hybrid integration of novel materials to address the limitations of existing integrated photonic platforms. Recently, graphene oxide (GO), with its large optical nonlinearity, high flexibility in altering its properties, and facile fabrication processes, has attracted significant attention, enabling many hybrid nonlinear integrated photonic devices with improved performance and novel capabilities. This paper reviews the applications of GO to nonlinear integrated photonics. First, an overview of GO's optical properties and the fabrication technologies needed for its on‐chip integration is provided. Next, the state‐of‐the‐art GO nonlinear integrated photonic devices are reviewed, followed by comparisons of the nonlinear optical performance of different integrated platforms incorporating GO as well as hybrid integrated devices including different kinds of 2D materials. Finally, the current challenges and future opportunities in this field are discussed.

8 citations

Journal ArticleDOI
TL;DR: In this article , an efficient in-situ nonlinear accelerator comprising a unique solution-processed two-dimensional (2D) MoS2 Opto-Resistive RAM Switch (ORS), which exhibits tunable nonlinear resistance switching that allow to introduce nonlinearity to the photonic neuron which overcomes the linear voltage-power relationship of typical photonic components.
Abstract: Photonic neural network has been sought as an alternative solution to surpass the efficiency and speed bottlenecks of electronic neural network. Despite that the integrated Mach-Zehnder Interferometer (MZI) mesh can perform vector-matrix multiplication in photonic neural network, a programmable in-situ nonlinear activation function has not been proposed to date, suppressing further advancement of photonic neural network. Here, we demonstrate an efficient in-situ nonlinear accelerator comprising a unique solution-processed two-dimensional (2D) MoS2 Opto-Resistive RAM Switch (ORS), which exhibits tunable nonlinear resistance switching that allow us to introduce nonlinearity to the photonic neuron which overcomes the linear voltage-power relationship of typical photonic components. Our reconfigurable scheme enables implementation of a wide variety of nonlinear responses. Furthermore, we confirm its feasibility and capability for MNIST handwritten digit recognition, achieving a high accuracy of 91.6%. Our accelerator constitutes a major step towards the realization of in-situ photonic neural network and pave the way for the integration of photonic integrated circuits (PIC).

7 citations

Journal ArticleDOI
TL;DR: In this paper , the authors propose meta-crystal slabs for general implementation of optical convolution, and numerically demonstrate several low-order differentiation kernels with a Gaussian envelope operating in transmission in the normal direction.
Abstract: Photonic structures have great potential in creating novel computing hardware due to their fast processing speed, low energy cost, and massive parallelism. Many algorithms in image processing and neural networks rely heavily on convolution and will benefit from efficient optical implementation of convolution. Here we propose meta-crystal slabs for a general implementation of optical convolution. Through an optimization approach, we design structures to perform a wide variety of convolution kernels. In particular, we numerically demonstrate several low-order differentiation kernels with a Gaussian envelope operating in transmission in the normal direction. Our structures are very compact and compute directly on the incident image fields. Our work may lead to high-performance optical computing hardware, and it also points to the possibility of creating novel optical components with volumetric metamaterials for imaging and sensing applications.

7 citations

Proceedings ArticleDOI
06 Jun 2021
TL;DR: A non-volatile optical memory element integrated in silicon photonics for low-power reconfigurable photonic circuits and neural networks and stable transmission states are demonstrated.
Abstract: We demonstrate a non-volatile optical memory element integrated in silicon photonics for low-power reconfigurable photonic circuits and neural networks. Stable transmission states are set by manipulating ferroelectric domains in BaTiO 3 films embedded in photonic waveguides.

7 citations

Proceedings ArticleDOI
08 Mar 2020
TL;DR: A taper-less III-V/Si hybrid MOS optical phase shifter that enables low insertion loss despite no taper, with keeping high modulation efficiency owing to strong electron confinement at the MOS interface is presented.
Abstract: We present proof-of-concept taper-less III-V/Si hybrid MOS optical phase shifter. An ultrathin InP membrane enables low insertion loss despite no taper, with keeping high modulation efficiency owing to strong electron confinement at the MOS interface.

7 citations

References
More filters
Proceedings Article
03 Dec 2012
TL;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

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.

46,982 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.

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))....

    [...]

Journal ArticleDOI
28 Jul 2006-Science
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

Journal ArticleDOI
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]....

    [...]