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: This study paves the way for directly utilizing the fluctuating physics inherent in ring lasers, or integrated photonics technologies in general, for achieving or accelerating intelligent functionality.
Abstract: Efficient and accurate decision making is gaining increased importance with the rapid expansion of information communication technologies including artificial intelligence. Here, we propose and experimentally demonstrate an on-chip, integrated photonic decision maker based on a ring laser. The ring laser exhibits spontaneous switching between clockwise and counter-clockwise oscillatory dynamics; we utilize such nature to solve a multi-armed bandit problem. The spontaneous switching dynamics provides efficient exploration to find the accurate decision. On-line decision making is experimentally demonstrated including autonomous adaptation to an uncertain environment. This study paves the way for directly utilizing the fluctuating physics inherent in ring lasers, or integrated photonics technologies in general, for achieving or accelerating intelligent functionality.
27 citations
Journal Article•
TL;DR: In this paper, a photonic routing architecture that can efficiently utilize the space of multi-plane (3D) photonic integration was proposed and experimentally demonstrated. But, the authors did not consider the impact of phase velocity mapping.
Abstract: We propose and experimentally demonstrate a photonic routing architecture that can efficiently utilize the space of multi-plane (3D) photonic integration. A wafer with three planes of amorphous silicon waveguides was fabricated and characterized, demonstrating < 3 × 1 0 − 4 dB loss per out-of-plane waveguide crossing, 0.05 ± 0.02 dB per interplane coupler, and microring resonators on three planes with a quality factors up to 8.2 × 1 0 4 . We also explore a phase velocity mapping strategy to mitigate the cross talk between co-propagating waveguides on different planes. These results expand the utility of 3D photonic integration for applications such as optical interconnects, neuromorphic computing and optical phased arrays.
26 citations
TL;DR: A free-space optical ANN with diffraction-based linear weight summation and nonlinear activation enabled by the saturable absorption of thermal atoms is presented, demonstrating image classification of handwritten digits using only a single layer and observing 6% improvement in classification accuracy due to the optical nonlinearity compared to a linear model.
Abstract: As artificial neural networks (ANNs) continue to make strides in wide-ranging and diverse fields of technology, the search for more efficient hardware implementations beyond conventional electronics is gaining traction In particular, optical implementations potentially offer extraordinary gains in terms of speed and reduced energy consumption due to the intrinsic parallelism of free-space optics At the same time, a physical nonlinearity—a crucial ingredient of an ANN—is not easy to realize in free-space optics, which restricts the potential of this platform This problem is further exacerbated by the need to also perform the nonlinear activation in parallel for each data point to preserve the benefit of linear free-space optics Here, we present a free-space optical ANN with diffraction-based linear weight summation and nonlinear activation enabled by the saturable absorption of thermal atoms We demonstrate, via both simulation and experiment, image classification of handwritten digits using only a single layer and observed 6% improvement in classification accuracy due to the optical nonlinearity compared to a linear model Our platform preserves the massive parallelism of free-space optics even with physical nonlinearity, and thus opens the way for novel designs and wider deployment of optical ANNs
26 citations
Cites background from "Deep learning with coherent nanopho..."
...demonstrated an electronic-optical hybrid neural network, in which the output of an integrated photonic mesh was outsourced to an external computer for nonlinear processing [4]....
[...]
TL;DR: In this paper, a recent progress in neuromorphic computing enabled by emerging two-dimensional (2D) materials is introduced from devices design and hardware implementation to system integration, shedding light on its great potential for artificial intelligence applications.
Abstract: Conventional computing based on von Neumann architecture cannot satisfy the demands of artificial intelligence (AI) applications anymore. Neuromorphic computing, emulating structures and principles based on the human brain, provides an alternative and promising approach for efficient and low consumption information processing. Herein, recent progress in neuromorphic computing enabled by emerging two-dimensional (2D) materials is introduced from devices design and hardware implementation to system integration. Especially, the advances of hopeful artificial synapses and neurons utilizing the resistive-switching-based devices, 2D ferroelectric-based memories and transistors, ultrafast flash, and promising transistors with attractive structures are highlighted. The device features, performance merits, bottlenecks, and possible improvement strategies, along with large-scale brain-inspired network fulfillment, are presented. Challenges and prospects of system application for neuromorphic computing are briefly discussed, shedding light on its great potential for AI.
26 citations
26 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]....
[...]