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
Photonic spiking neural networks with event-driven femtojoule optoelectronic neurons based on Izhikevich-inspired model
TL;DR: In this paper , an event-driven neuron inspired by the Izhikevich model incorporating both excitatory and inhibitory spiking inputs and producing optical spiking outputs was presented.
Posted Content
Quantum Earth Mover's Distance: A New Approach to Learning Quantum Data
TL;DR: In this paper, a quantum Wasserstein generative adversarial network (qWGAN) is proposed, which takes advantage of the quantum earth mover's (EM) distance and provides an efficient means of performing learning on quantum data.
Journal ArticleDOI
Dispersion-tunable photonic topological waveguides
TL;DR: In this article , a topological valley waveguide by utilizing bilayer designer plasmonic structures is constructed, accomplished with dispersion tunings by altering interlayer distance, achieving a 61%-relative-tuning range of frequency, with a tunable relative bandwidth up to 16%.
Journal ArticleDOI
Implementing fractional Fourier transform and solving partial differential equations using acoustic computational metamaterials in space domain
TL;DR: The acoustic wave computational metamaterial is designed, and the simulation realizes the spatial domain fractional Fourier transform and partial differential equation calculation.
Journal ArticleDOI
Optical Neural Network Based on Synthetic Nonlinear Photonic Lattices
TL;DR: In this article , a synthetic photonic lattice based on coupled optical loops can be utilized as a feed-forward neural network for processing of optical pulse sequences in time domain, and the optical system is trained to restore an initial shape of the pulse train from the signal distorted due to linear dispersion in a fiber-optic link.
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.