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
All Optical Integrate and Fire Neuromorphic Node Based on Single Section Quantum Dot Laser
TL;DR: In this paper, the authors provided numerical results concerning an all-optical inhibitory integrate and fire neuron based on a single section quantum-dot InAs/GaAs laser and employed a detailed multi-population approach that accommodates electron-hole dynamics and can efficiently describe waveband transitions from both the ground and excited energy state.
Journal ArticleDOI
Entangled-photon decision maker.
Nicolas Chauvet,David Jegouso,Benoît Boulanger,Hayato Saigo,Kazuya Okamura,Hirokazu Hori,Aurélien Drezet,Serge Huant,Guillaume Bachelier,Makoto Naruse,Makoto Naruse +10 more
TL;DR: In this paper, the authors provided experimental evidence that entangled photons physically resolve the competitive multi-armed bandit problem in the 2-arms 2-players case, maximizing the social rewards while ensuring equality, and demonstrated that deception or outperforming the other player by receiving a greater reward cannot be accomplished in a polarization-entangled-photon-based system, while deception is achievable in systems based on classical polarization-correlated photons with fixed polarizations.
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: In this paper, an approach to apply reinforcement learning algorithms within modern-day photonic technologies is presented, based on single-photon evolution on a tree structure of tunable beamsplitters, which is simple, easy to implement and an integration in quantum optics applications appears to be within the reach of near-term technology.
Journal ArticleDOI
Rapid Classification of Quantum Sources Enabled by Machine Learning
Zhaxylyk A. Kudyshev,Simeon Bogdanov,Theodor Isacsson,Theodor Isacsson,Alexander V. Kildishev,Alexandra Boltasseva,Vladimir M. Shalaev +6 more
TL;DR: In this paper, a supervised machine learning-based classification of quantum emitters as "single" or "not-single" based on their sparse autocorrelation data is implemented. But the classification accuracy of over 90% within an integration time of less than a second, realizing roughly a hundredfold speedup compared to the conventional, Levenberg-Marquardt approach.
Journal ArticleDOI
Programmable chalcogenide-based all-optical deep neural networks
T. Teo,Xiaoxuan Ma,Ernest Pastor,Hao Wang,Jonathan K. George,Joel K. W. Yang,Simon Wall,Mario Miscuglio,J. Simpson,Volker J. Sorger +9 more
TL;DR: In this paper, a passive all-chalcogenide all-optical perceptron scheme was proposed to perform energy-efficient alloptical neural classifications at rates greater than 1 GHz.
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.