Deep learning with coherent nanophotonic circuits

TL;DR: In this paper, a manifold learning approach based on manifold learning for knowledge discovery and inverse design with minimal complexity in photonic nanostructures is presented. But it is limited to pre-selected and usually over-complex structures.

TL;DR: In this paper, a systematic evaluation of the inference performance of trained popular deep learning models for image classification deployed on analog devices has been carried out, where additive white Gaussian noise has been added to the weights of the trained models during inference.

TL;DR: A reinforcement learning algorithm for on-site learning and discrete optimization algorithm for digital coding are proposed, making PAIM have autonomous intelligence ability and perform self-learning tasks without the support of extra computer.

TL;DR: A photonics-enabled spiking timing-dependent convolutional neural network is proposed by manipulating photonics multidimensional parameters in terms of wavelength, temporal and spatial, which breaks the traditional CNN architecture mapping from a spatially parallel to a time-dependent series structure.

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.