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
11 Mar 2018
TL;DR: Efficient, low-loss phase modulation using III-V/Si hybrid MOS capacitor on Si photonics platform is presented, which will be an essential building-block for universal photonic integrated circuits monolithically integrated with driver circuits based on InGaAs MOSFETs.
Abstract: We present efficient, low-loss phase modulation using III-V/Si hybrid MOS capacitor on Si photonics platform, which will be an essential building-block for universal photonic integrated circuits monolithically integrated with driver circuits based on InGaAs MOSFETs.
3 citations
TL;DR: A lateral, planar fiber-to-waveguide coupling strategy for photonic integrated circuits with diffraction grating couplers using angle-polished silica waveguide blocks fabricated with well-established planar lightwave circuit technologies is demonstrated.
Abstract: We demonstrate a lateral, planar fiber-to-waveguide coupling strategy for photonic integrated circuits with diffraction grating couplers using angle-polished silica waveguide blocks fabricated with well-established planar lightwave circuit technologies. Compared to the conventional lateral coupling scheme with angle-polished fibers, the demonstrated scheme can significantly decrease the diverging distance between the reflective angle-polished facet and the grating couplers, and thereby maintains the overall coupling efficiency and alignment tolerances of the vertical coupling approach. The proposed method shows a small penalty in coupling efficiency (< 0.1 dB), and in-plane (out-of-plane) alignment tolerance for 1 dB excess loss is approximately 5 µm (9 µm).
3 citations
10 May 2020
TL;DR: This work utilizes machine learning algorithm to design integrated photonic meta-systems, and experimentally demonstrated the device performance.
Abstract: We utilize machine learning algorithm to design integrated photonic meta-systems, and experimentally demonstrated the device performance.
3 citations
Cites background from "Deep learning with coherent nanopho..."
...As deep learning systems usually require large number of neurons, integrated photonics with high density of optical components is an ideal platform [3]....
[...]
...The input wave of the (l + 1)-th layer can be expressed as [3]:...
[...]
Posted Content•
TL;DR: A silicon photonics-based architecture for convolutional neural networks that harnesses the phase property of light to perform FFTs efficiently by executing the convolution as a multiplication in the Fourier-domain is presented.
Abstract: The technologically-relevant task of feature extraction from data performed in deep-learning systems is routinely accomplished as repeated fast Fourier transforms (FFT) electronically in prevalent domain-specific architectures such as in graphics processing units (GPUs). However, electronics systems are limited with respect to power dissipation and delay, both, due to wire-charging challenges related to interconnect capacitance. Here we present a silicon photonics-based architecture for convolutional neural networks that harnesses the phase property of light to perform FFTs efficiently by executing the convolution as a multiplication in the Fourier-domain. The algorithmic executing time is determined by the time-of-flight of the signal through this photonic reconfigurable passive FFT filter circuit and is on the order of 10s of picosecond. A sensitivity analysis shows that this optical processor must be thermally phase stabilized corresponding to a few degrees. Furthermore, we find that for a small sample number, the obtainable number of convolutions per {time-power-chip area) outperforms GPUs by about 2 orders of magnitude. Lastly, we show that, conceptually, the optical FFT and convolution-processing performance is indeed directly linked to optoelectronic device-level, and improvements in plasmonics, metamaterials or nanophotonics are fueling next generation densely interconnected intelligent photonic circuits with relevance for edge-computing 5G networks.
3 citations
Cites background from "Deep learning with coherent nanopho..."
...Ref [8] or alternatively with emerging modulator-concepts featuring heterogeneous integration of strong-index changes materials such as transparent conductive oxides featuring strong light matter interaction near epsilon near zero (ENZ) operating points...
[...]
...For the neuron interconnectivity the broadcast and weight protocol use wavelength-division-multiplexing (WDM) to assign a dedicated optical wavelength to each neuron, and multiplexes all signals onto a common photonic bus, thus enabling fully-connected NN [6-8] or all-optical [12]....
[...]
...Photonic or electro-optic concept for the neuron implementation include, amongst others, electro-optic analog weighting [8-10] and spiking-based solutions e....
[...]
...In this context, the rise of emerging neuromorphic platforms for artificial intelligence (AI) acceleration include optical [2-5] and photonics neural networks (NN) [6-8], which also contain emerging plasmonic and meta-materials for both the dot-product linear synaptic weights, and the nonlinear activation function [9,10]....
[...]
TL;DR: In this paper, a reversible programmable photonic integrated circuits (PIC) using a responsive polyelectrolyte multilayer (PEM) cladding is presented, where reversible de-swelling of PEMs by consecutive exposure to acidic and neutral pH solutions yields highly contrasting refractive index changes in the dry film.
Abstract: Reversibly programmable photonic integrated circuits (PICs) that can facilitate multifunctionality have been long sought after to deliver user-level design flexibility. Issues like complicated control, continuous power consumption, and high optical losses hinder their large-scale adaptation. In this work, a novel approach toward programmable photonics using a responsive polyelectrolyte multilayer (PEM) cladding is presented. Reversible (de)swelling of PEMs by consecutive exposure to acidic and neutral pH solutions yields highly contrasting refractive index changes in the dry film. Utilizing this effect, an easily applied technique for programming photonic integrated devices with two different approaches, complete and area-selective deposition, for several reversible cycles is demonstrated. These devices operate at two distinct states that are virtually lossless and nonvolatile. This proof-of-concept demonstration is suitable for various photonic integration platforms to facilitate reconfigurable photonic processors, static memories, and fine-tuning of fabrication related limitations. Therefore, these results are the first step toward PEM-assisted reversibly programmable multipurpose PICs for low-cost mass production.
3 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]....
[...]