Deep learning with coherent nanophotonic circuits

TL;DR: In this paper , a novel hybrid photonic delay-based reservoir computers (RC) scheme is proposed, in which input data is first preprocessed through several convolutional layers, either trained or untrained, digitally to generate novel feature maps.

TL;DR: In this article, the metal microheater is integrated on the side of the waveguide rather than on the top, and the tuning efficiency is significantly enhanced, and response time as fast as 2

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.

TL;DR: In this paper, a fully parallel and fully implemented photonic neural network can be realized using spatially distributed modes of an efficient and fast semiconductor laser, and all neural network connections are realized in hardware, and their processor produces results without pre- or postprocessing.

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.

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.

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.

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.