Deep learning with coherent nanophotonic circuits
Yichen Shen,Nicholas C. Harris,Scott Skirlo,Dirk Englund,Marin Soljacic +4 more
- 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.
read more
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
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
UV photonic integrated circuits for far-field structured illumination autofluorescence microscopy
Chu Ying Lin,Juan Santo Domingo Penaranda,Jolien Dendooven,Christophe Detavernier,David Schaubroeck,Nico Boon,Roel Baets,Nicolas Le Thomas +7 more
TL;DR: In this paper , photonic integrated circuits made of aluminum oxide thin layers that are compatible with both UV light and high-volume manufacturing are presented. And they enable super-resolved structured illumination microscopy with conventional wide-field microscopes and without modifying the usual protocol for handling the object to be imaged.
Electrical Programmable Low-loss high cyclable Nonvolatile Photonic Random-Access Memory
Jiawei Meng,Nicola Peserico,Xiaoxuan Ma,Yifei Zhang,C. Popescu,Myung Gyu Kang,Mario Miscuglio,K. Richardson,Juejun Hu,Volker J. Sorger +9 more
TL;DR: In this paper , a photonic random access memory with vanishing low optical loss was proposed, which can achieve more than half a million switching cycles and realize electrical programmability on-chip.
25
Wavelength-division-multiplexing (WDM)-based integrated electronic–photonic switching network (EPSN) for high-speed data processing and transportation
TL;DR: A WDM-based electronic–photonic switching network (EPSN) is proposed to realize the functions of the binary decoder and the multiplexer, which are fundamental elements in microprocessors for data transportation and processing.
25
Dispersion engineered metasurfaces for broadband, high-NA, high-efficiency, dual-polarization analog image processing
Michele Cotrufo,Aanchal Arora,Sahitya Singh,Andrea Alù +3 more
TL;DR: Dispersion engineered metasurfaces achieve high-efficiency, broadband, high-NA, and dual-polarization analog image processing.
All-Optical Nonlinear Activation Function Based on Germanium Silicon Hybrid Asymmetric Coupler
TL;DR: In this article , an all-optical implementation of a nonlinear activation function based on germanium silicon hybrid integration was proposed and demonstrated for optical neural networks (ONNs) to achieve more various functions.
25
References
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
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.
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.
67K
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.
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.
Related Papers (5)
[...]