Parallel multi-thread processing in advanced intelligent processors is the core to realize high-speed and high-capacity signal processing systems.Optical neural network(ONN)has the native advantages of high parallelization,large bandwidth,and low power consumption to meet the demand of big data.Here,...
highlighting the advantages of chip-based complex-valued networks by optical computing. This results in a complex-valued neural network that integrates input preparation, weight multiplication and output generation in a single photonic chip. Meanwhile, previous...
Using techniques based on the second-order properties of the error function, we show that very little accuracy on the weights and states is required in the first layers of the network. Interestingly, the best digit-recognition network is also the easiest to implement on a chip. 展开 ...
An I/O bandwidth commensurate with a dramatically increasing on-chip computational capability is highly desirable. Achieving this goal using board-level co... H Cho,P Kapur,KC Saraswat - 《Journal of Lightwave Technology》 被引量: 335发表: 2004年 Gemini: an optical interconnection network for ...
Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimen...
Optical neural networks (ONNs) have become competitive candidates for the next generation of high-performance neural network accelerators because of their ... S Xu,J Wang,R Wang,... - 《Optics Express》 被引量: 0发表: 2019年 On-Chip Communication Network for Efficient Training of Deep Convol...
examine how deep generative networks can learn geometric features in device distributions and even be configured to serve as robust global optimizers. Fundamental data-science concepts framed within the context of photonics are also discussed, including the network-training process, delineation of ...
In order to offer operating information to the monitoring system of a chip refiner, a neural network classifier is proposed for identifying the acoustic em... Y Jian,GD Dumont - Proceedings of SPIE - The International Society for Optical Engineering 被引量: 13发表: 1992年 Structural Integrity ...
based on which of the output neurons had the largest value. The neural network was implemented and trained in PyTorch52. The training of the neural network was conducted exclusively on a digital computer (our optical experiments perform neural-network inference only). To improve the robustness of...
In the optical domain, despite advances in photonic computation15,16,17, the lack of scalable on-chip optical non-linearity and the loss of photonic devices limit the scalability of optical deep networks. Here we report an integrated end-to-end photonic deep neural network (PDNN) that performs...