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
Posted Content
Electromagnetic Eigenvalue Problems and Nonhermitian Effects in Linear and Saturable Scattering
TL;DR: In this paper, the authors studied degenerate coherent perfect absorption (CPA) from cavities with a linear dielectric response to include the saturating nonlinearity and dispersion of a two-level absorbing medium, and showed that the SALT algorithm can also be used to find the saturable CPA modes through a simple mapping.
Journal ArticleDOI
Metamaterials: From fundamental physics to intelligent design
TL;DR: In this paper , the authors introduce the basic concepts, working principles, design methods, and applications of metamaterials, and then focus on the rapidly developing meta-materials research combined with AI algorithms.
Patent
Programmable photonic processing
TL;DR: A programmable photonic integrated circuit as discussed by the authors implements arbitrary linear optics transformations in the spatial mode basis with high fidelity under a realistic fabrication model, and it is shown that programmability dramatically improves device tolerance to fabrication imperfections and enables a single device to implement a broad range of both quantum and classical linear optics experiments.
Journal ArticleDOI
Manifold Learning for Knowledge Discovery and Intelligent Inverse Design of Photonic Nanostructures: Breaking the Geometric Complexity
TL;DR: In this article , a new approach based on manifold learning for knowledge discovery and inverse design with minimal complexity in photonic nanostructures is presented. But it is limited to preselected and usually overcomplex structures.
Journal ArticleDOI
Metasurface on integrated photonic platform: from mode converters to machine learning
Zi Wang,Yahui Xiao,Kun Liao,Tiantian Li,Haoqian Song,H. S. Chen,S. Z. Uddin,Dun Mao,Feifan Wang,Zhiping Zhou,Bo Yuan,Wei Xiang Jiang,Nicolas K. Fontaine,Amit Agrawal,Alan E. Willner,Xiaoyong Hu,Tingyi Gu +16 more
TL;DR: In this article , an alternative way of defining the light flow in the integrated photonic platform, using arrays of subwavelength meta-atoms or metalines for guiding the diffraction and interference of light.
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.