Deep learning with coherent nanophotonic circuits
Yichen Shen,Nicholas C. Harris,Scott Skirlo,Dirk Englund,Marin Soljacic +4 more
- Vol. 11, Iss: 7, pp 441-446
Reads0
Chats0
TLDR
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.read more
Citations
More filters
Journal ArticleDOI
A small microring array that performs large complex-valued matrix-vector multiplication
TL;DR: Wang et al. as mentioned in this paper proposed a photonic complex matrix-vector multiplier chip, which can support arbitrary large-scale and complex-valued matrix computation, and further demonstrate Walsh-Hardmard transform, discrete cosine transform, and image convolutional processing.
Journal ArticleDOI
Neuronal coupling benefits the encoding of weak periodic signals in symbolic spike patterns
TL;DR: In this paper, the authors analyze the activity of a group of neurons when they all perceive a weak periodic signal and find that the probabilities of the spike patterns depend on the signal's amplitude and period, and thus, the patterns' probabilities encode the information of the signal.
Journal ArticleDOI
Bistable All‐Optical Devices Based on Nonlinear Epsilon‐Near‐Zero (ENZ) Materials
TL;DR: In this article , a novel bistable resonator-free all-optical waveguide device based on indium tin oxide as nonlinear epsilon-near-zero material providing a cost-efficient and high-performance binarity photonic platform is proposed.
Posted Content
Orthogonality of Diffractive Deep Neural Networks
TL;DR: In this article, the inner product of any two light fields in D2NN is invariant and the D2N act as a unitary transformation for optical fields, which implies that the DNN is not only suitable for the classification of general objects but also more suitable for applications aim to the optical orthogonal modes.
Journal ArticleDOI
Miniature Otto Prism Coupler for Integrated Photonics
Kirill R. Safronov,Vladimir O. Bessonov,Daniil V. Akhremenkov,M. A. Sirotin,Maria N. Romodina,Evgeny V. Lyubin,Irina V. Soboleva,Andrey A. Fedyanin +7 more
TL;DR: In this article , a 3D out-of-plane coupler is introduced, which is a microscale prism exploiting frustrated total internal reflection in the Otto configuration to excite surface electromagnetic waves or near surface waveguide modes.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
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.
Journal ArticleDOI
Deep learning
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.
Journal ArticleDOI
Human-level control through deep reinforcement learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Andrei Rusu,Joel Veness,Marc G. Bellemare,Alex Graves,Martin Riedmiller,Andreas K. Fidjeland,Georg Ostrovski,Stig Petersen,Charles Beattie,Amir Sadik,Ioannis Antonoglou,Helen King,Dharshan Kumaran,Daan Wierstra,Shane Legg,Demis Hassabis +18 more
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.
Journal ArticleDOI
Reducing the Dimensionality of Data with Neural Networks
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.
Journal ArticleDOI
Deep learning in neural networks
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.