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: It is proved that the N-D2NN model based on 10.6 μm wavelength has excellent representation ability, which enables them to perform classification learning tasks of the MNIST handwritten digital dataset and Fashion-MNIST dataset well, respectively.
Abstract: A photonic artificial intelligence chip is based on an optical neural network (ONN), low power consumption, low delay, and strong antiinterference ability. The all-optical diffractive deep neural network has recently demonstrated its inference capabilities on the image classification task. However, the size of the physical model does not have miniaturization and integration, and the optical nonlinearity is not incorporated into the diffraction neural network. By introducing the nonlinear characteristics of the network, complex tasks can be completed with high accuracy. In this study, a nonlinear all-optical diffraction deep neural network (N-D2NN) model based on 10.6 μm wavelength is constructed by combining the ONN and complex-valued neural networks with the nonlinear activation function introduced into the structure. To be specific, the improved activation function of the rectified linear unit (ReLU), i.e., Leaky-ReLU, parametric ReLU (PReLU), and randomized ReLU (RReLU), is selected as the activation function of the N-D2NN model. Through numerical simulation, it is proved that the N-D2NN model based on 10.6 μm wavelength has excellent representation ability, which enables them to perform classification learning tasks of the MNIST handwritten digital dataset and Fashion-MNIST dataset well, respectively. The results show that the N-D2NN model with the RReLU activation function has the highest classification accuracy of 97.86% and 89.28%, respectively. These results provide a theoretical basis for the preparation of miniaturized and integrated N-D2NN model photonic artificial intelligence chips.
5 citations
Cites methods from "Deep learning with coherent nanopho..."
...A variety of methods for optical neural networks (ONN) have been proposed, including Hopfield networks with LED arrays [5], optoelectronic implementation of reservoir computing [5, 6], spiking recurrent networks with micron resonators [7, 8], and fully connected feedforward networks using Mach–Zehnder interferometers (MZIs) [9]....
[...]
TL;DR: In this paper , the authors use Time-Floquet physics to induce a strong nonlinear entanglement between signal inputs at different frequencies, enabling a power-efficient and versatile wave platform for analog deep learning involving a single, uniformly modulated dielectric layer and a scattering medium.
Abstract: Wave-based analog signal processing holds the promise of extremely fast, on-the-fly, power-efficient data processing, occurring as a wave propagates through an artificially engineered medium. Yet, due to the fundamentally weak non-linearities of traditional wave materials, such analog processors have been so far largely confined to simple linear projections such as image edge detection or matrix multiplications. Complex neuromorphic computing tasks, which inherently require strong non-linearities, have so far remained out-of-reach of wave-based solutions, with a few attempts that implemented non-linearities on the digital front, or used weak and inflexible non-linear sensors, restraining the learning performance. Here, we tackle this issue by demonstrating the relevance of Time-Floquet physics to induce a strong non-linear entanglement between signal inputs at different frequencies, enabling a power-efficient and versatile wave platform for analog extreme deep learning involving a single, uniformly modulated dielectric layer and a scattering medium. We prove the efficiency of the method for extreme learning machines and reservoir computing to solve a range of challenging learning tasks, from forecasting chaotic time series to the simultaneous classification of distinct datasets. Our results open the way for wave-based machine learning with high energy efficiency, speed, and scalability.
5 citations
25 Feb 2020
TL;DR: Despite its infancy, the biologically-accurate neuron already has exhibited an unprecedented potential to boost the hardware implementation of brain-like computation as well as leading a trend on neurorobotics and prosthetics.
Abstract: A new trend in brain-like computing is to develop more biologically realistic neurons in order to accurately replicate the computational power of the biological counterparts. The brain-like computing platforms based on these models that resemble the organization of neurons in brain would serve as a more efficient tool than traditional hardware. Recently, with the rapid development of neuromorphic devices, the realization of biologically-accurate neurons to fit these models becomes feasible. In view of this, we summarize the most recent progress on neuromorphic devices for achieving the essential neuronal information processing functions of a biological neuron. Despite its infancy, the biologically-accurate neuron already has exhibited an unprecedented potential to boost the hardware implementation of brain-like computation as well as leading a trend on neurorobotics and prosthetics. Challenges and perspectives are also addressed to shed light on future advances with respect to practical applications and t...
5 citations
TL;DR: In this article , an ultralow-loss silicon planar waveguide crossing operating in the O-band was experimentally demonstrated based on the Gaussian beam synthesis method, where elliptical parabolic inverted tapers were introduced to reduce the crossing loss.
Abstract: An ultralow-loss silicon planar waveguide crossing operating in the O-band was experimentally demonstrated based on the Gaussian beam synthesis method. Elliptical parabolic inverted tapers were introduced in our design to reduce the crossing loss. According to the measurement results, the proposed device exhibits an insertion loss of 0.008 dB, which is the lowest reported loss for planar silicon waveguide crossings operating in the O-band. The device exhibits a low crosstalk below -40 dB over a 40 nm wavelength range with a compact footprint of 18 × 18 µm2 and can be fabricated in a complementary metal-oxide-semiconductor-compatible process.
5 citations
TL;DR: This work demonstrates generalizable image reconstruction with the simplest of hybrid machine vision systems: linear optical preprocessors combined with no-hidden-layer, “small-brain” neural networks, capable of learning the image reconstruction from a range of coded diffraction patterns using two masks.
Abstract: Speed, generalizability, and robustness are fundamental issues for building lightweight computational cameras. Here we demonstrate generalizable image reconstruction with the simplest of hybrid machine vision systems: linear optical preprocessors combined with no-hidden-layer, “small-brain” neural networks. Surprisingly, such simple neural networks are capable of learning the image reconstruction from a range of coded diffraction patterns using two masks. We investigate the possibility of generalized or “universal training” with these small brains. Neural networks trained with sinusoidal or random patterns uniformly distribute errors around a reconstructed image, whereas models trained with a combination of sharp and curved shapes (the phase pattern of optical vortices) reconstruct edges more boldly. We illustrate variable convergence of these simple neural networks and relate learnability of an image to its singular value decomposition entropy of the image. We also provide heuristic experimental results. With thresholding, we achieve robust reconstruction of various disjoint datasets. Our work is favorable for future real-time low size, weight, and power hybrid vision: we reconstruct images on a 15 W laptop CPU with 15,000 frames per second: faster by a factor of 3 than previously reported results and 3 orders of magnitude faster than convolutional neural networks.
5 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]....
[...]