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
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
Far-Field Subwavelength Acoustic Imaging by Deep Learning
TL;DR: In this paper, a new acoustic technique involving machine learning could lead to cheaper and faster high-resolution medical imaging, which could also lead to faster and more accurate high-definition medical imaging.
Journal ArticleDOI
Prediction of spectral absorption of anisotropic α-MoO3 nanostructure using deep neural networks
TL;DR: In this paper , the spectral absorption of anisotropic α-MoO3 nanostructure was predicted using deep neural networks (DNNs), and the effect of the incident angle on the absorption spectrum was considered, and the absorber was found to be angle insensitive over a wide angle range.
Journal ArticleDOI
Photonic architecture for reinforcement learning
Fulvio Flamini,Arne Hamann,Sofiene Jerbi,Lea M. Trenkwalder,Hendrik Poulsen Nautrup,Hans J. Briegel +5 more
TL;DR: The blueprint for a photonic implementation of an active learning machine incorporating contemporary algorithms such as SARSA, Q-learning, and projective simulation is presented, showing that realistic levels of experimental noise can be tolerated or even be beneficial for the learning process.
Journal ArticleDOI
Mathematical operations and equation solving with reconfigurable metadevices
TL;DR: In this article , the authors report the theory and design of wave-based metastructures using tunable elements capable of solving integral/differential equations in a fully-reconfigurable fashion.
Posted Content
Stability of Self-Configuring Large Multiport Interferometers.
TL;DR: In this paper, the authors propose a self-configuration scheme for triangular meshes that requires only external detectors and works without prior knowledge of the component imperfections. And they extend this scheme to the rectangular mesh by adding a single array of detectors along the diagonal.
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.