Express Wavenet -- a low parameter optical neural network with random shift wavelet pattern
Express Wavenet is an improved optical diffractive neural network. At each layer, it uses wavelet-like pattern to modulate the phase of optical waves. For input image with n2 pixels, express wavenet reduce parameter number from O(n2) to O(n). Only need one percent of the parameters, and the accuracy is still very high. In the MNIST dataset, it only needs 1229 parameters to get accuracy of 92%, while the standard optical network needs 125440 parameters. The random shift wavelets show the characteristics of optical network more vividly. Especially the vanishing gradient phenomenon in the training process. We present a modified expressway structure for this problem. Experiments verified the effect of random shift wavelet and expressway structure. Our work shows optical diffractive network would use much fewer parameters than other neural networks. The source codes are available at https://github.com/closest-git/ONNet.
Code (1)
Similar Papers 제목 키워드 기반
Multi-task WaveNet: A Multi-task Generative Model for Statistical Parametric Speech Synthesis without Fundamental Frequency Conditions
This paper introduces an improved generative model for statistical parametric speech synthesis (SPSS) based on WaveNet under a multi-task learning framework. Different from the original WaveNet model, the proposed Multi-…
Multi-Task LearningPredictionSpeech SynthesisTracking System for Optical Mobile Communication and the Design Rules
Free space optical communication has been applied in many scenarios because of its security, low cost and high rates. In such scenarios, a tracking system is necessary to ensure an acceptable signal power. Free space opt…
WaveNet: Wave-Aware Image Enhancement
As a low-level vision task, image enhancement is widely used in various computer vision applications. Recently, multiple methods combined with CNNs, MLP, Transformer, and the Fourier transform have achieved promising res…
Image EnhancementImage RetouchingLow-Light Image EnhancementExact gradients for linear optics with single photons
Though parameter shift rules have drastically improved gradient estimation methods for several types of quantum circuits, leading to improved performance in downstream tasks, so far they have not been transferable to lin…
Gradients of unitary optical neural networks using parameter-shift rule
This paper explores the application of the parameter-shift rule (PSR) for computing gradients in unitary optical neural networks (UONNs). While backpropagation has been fundamental to training conventional neural network…