No abstract

Despite various optical realizations of convolutional neural networks (CNNs), optical implementation of nonlinear activation functions and pooling operations are still challenging problems. In this regard, this paper proposes an optical saturable absorption nonlinearity and its atomic-level model, as well as two various optical pooling operations, namely optical average pooling and optical motion pooling, by means of 4f optical correlators. Proposing these optical building blocks not only speed up the neural networks due to negligible optical processing latency, but also facilitate the concatenation of optical convolutional layers with no optoelectrical conversions in-between, as the significant bottlenecks of implementing photonic CNNs. Furthermore, the proposed optical motion pooling layer increases the translation invariance property of CNNs, avoiding the inclusion of all corresponding translated images for the training procedure, and hence, increases the training speed of the neural network. The classification accuracy of the proposed optical convolutional layer is evaluated as the first layer of a customized version of AlexNet architecture, named as OP-AlexNet, for classification of Kaggle Cats and Dog challenge, CIFAR-10, and MNIST datasets, as 83.76%, 72.82%, and 99.25%, respectively, by using optical average pooling.

No abstract

No abstract

This paper proposes a novel topology for optical Network on Chip (NoC) architectures with the key advantages of regularity, vertex symmetry, scalability to large scale networks, constant node degree, and simplicity. Moreover, we propose a minimal deterministic routing algorithm for the proposed topology which leads to small and simple photonic routers. Built upon our novel network topology, we present a scalable all-optical NoC, referred to as 2D-HERT, which offers passive routing of optical data streams based on their wavelengths. Utilizing wavelength routing method along with Wavelength Division Multiplexing technique, our proposed optical NoC eliminates the need for electrical resource reservation. We compare performance of the proposed architecture against electrical NoCs and alternative all-optical onchip architectures under various synthetic traffic patterns. Averaging through different traffic patterns, achieves average perpacket power reduction of 53%, 45%, and 95% over optical crossbar, λ-router, and electrical Torus, respectively.

No abstract

No abstract

In this study, optical technology is considered as SA issues' solution with the potential ability to increase the speed, overcome memory-limitation, reduce power consumption, and increase output accuracy. So we examine the effect of bio-data encoding and the creation of input images on the pattern-recognition error-rate at the output of optical Vander-lugt correlator. Moreover, we present a genetic algorithm-based coding approach, named as GAC, to minimize output noises of cross-correlating data. As a case study, we adopt the proposed coding approach within a correlation-based optical architecture for counting k-mers in a DNA string. As verified by the simulations on Salmonella whole-genome, we can improve sensitivity and speed more than 86% and 81%, respectively, compared to BLAST by using coding set generated by GAC method fed to the proposed optical correlator system. Moreover, we present a comprehensive report on the impact of 1D and 2D cross-correlation approaches, as-well-as various coding parameters on the output noise, which motivate the system designers to customize the coding sets within the optical setup.