中文
相关论文

相关论文: Neural Networks-based Equalizers for Coherent Opti…

200 篇论文

Because deep neural networks (DNNs) rely on a large number of parameters and computations, their implementation in energy-constrained systems is challenging. In this paper, we investigate the solution of reducing the supply voltage of the…

The intensive computation and memory requirements of generative adversarial neural networks (GANs) hinder its real-world deployment on edge devices such as smartphones. Despite the success in model reduction of CNNs, neural network…

神经与进化计算 · 计算机科学 2019-01-25 Peiqi Wang , Dongsheng Wang , Yu Ji , Xinfeng Xie , Haoxuan Song , XuXin Liu , Yongqiang Lyu , Yuan Xie

Neural network models and deep models are one of the leading and state of the art models in machine learning. Most successful deep neural models are the ones with many layers which highly increases their number of parameters. Training such…

机器学习 · 计算机科学 2018-07-17 Soufiane Belharbi

Numerous studies have recently focused on incorporating different variations of equivariance in Convolutional Neural Networks (CNNs). In particular, rotation-equivariance has gathered significant attention due to its relevance in many…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Robin Ghyselinck , Valentin Delchevalerie , Bruno Dumas , Benoît Frénay

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

机器学习 · 计算机科学 2018-06-08 Samet Oymak

Convolutional Neural Networks (CNNs) have achieved comparable error rates to well-trained human on ILSVRC2014 image classification task. To achieve better performance, the complexity of CNNs is continually increasing with deeper and bigger…

计算机视觉与模式识别 · 计算机科学 2014-12-30 Wei Yu , Kuiyuan Yang , Yalong Bai , Hongxun Yao , Yong Rui

Quantization, a commonly used technique to reduce the memory footprint of a neural network for edge computing, entails reducing the precision of the floating-point representation used for the parameters of the network. The impact of such…

机器学习 · 计算机科学 2019-03-27 Abhishek Murthy , Himel Das , Md Ariful Islam

Neural networks enjoy widespread success in both research and industry and, with the imminent advent of quantum technology, it is now a crucial challenge to design quantum neural networks for fully quantum learning tasks. Here we propose…

The role of quantization within implicit/coordinate neural networks is still not fully understood. We note that using a canonical fixed quantization scheme during training produces poor performance at low-rates due to the network weight…

计算机视觉与模式识别 · 计算机科学 2024-10-14 Cameron Gordon , Shin-Fang Chng , Lachlan MacDonald , Simon Lucey

Quantization can improve the execution latency and energy efficiency of neural networks on both commodity GPUs and specialized accelerators. The majority of existing literature focuses on training quantized DNNs, while this work examines…

机器学习 · 计算机科学 2019-05-24 Ritchie Zhao , Yuwei Hu , Jordan Dotzel , Christopher De Sa , Zhiru Zhang

Large nonlinear recurrent neural networks with random couplings generate high-dimensional, potentially chaotic activity whose structure is of interest in neuroscience and other fields. A fundamental object encoding the collective structure…

无序系统与神经网络 · 物理学 2026-05-06 David G. Clark

Convolutional neural networks (CNNs) show outstanding performance in many image processing problems, such as image recognition, object detection and image segmentation. Semantic segmentation is a very challenging task that requires…

计算机视觉与模式识别 · 计算机科学 2019-07-12 Fan Jia , Jun Liu , Xue-cheng Tai

Deep neural networks (DNNs) are powerful machine learning models and have succeeded in various artificial intelligence tasks. Although various architectures and modules for the DNNs have been proposed, selecting and designing the…

神经与进化计算 · 计算机科学 2018-01-24 Shinichi Shirakawa , Yasushi Iwata , Youhei Akimoto

The translational equivariant nature of Convolutional Neural Networks (CNNs) is a reason for its great success in computer vision. However, networks do not enjoy more general equivariance properties such as rotation or scaling, ultimately…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Zikai Sun , Thierry Blu

The "CNN-RNN" design pattern is increasingly widely applied in a variety of image annotation tasks including multi-label classification and captioning. Existing models use the weakly semantic CNN hidden layer or its transform as the image…

计算机视觉与模式识别 · 计算机科学 2016-11-18 Feng Liu , Tao Xiang , Timothy M. Hospedales , Wankou Yang , Changyin Sun

Different from developing neural networks (NNs) for general-purpose processors, the development for NN chips usually faces with some hardware-specific restrictions, such as limited precision of network signals and parameters, constrained…

神经与进化计算 · 计算机科学 2018-01-19 Yu Ji , YouHui Zhang , WenGuang Chen , Yuan Xie

This paper presents a comprehensive study on the scalability challenges and opportunities in quantum communication networks, with the goal of determining parameters that impact networks most as well as the trends that appear when scaling…

新兴技术 · 计算机科学 2024-09-16 Connor Howe , Mohsin Aziz , Ali Anwar

Optical neural networks present distinct advantages over traditional electrical counterparts, such as accelerated data processing and reduced energy consumption. While coherent light is conventionally employed in optical neural networks,…

光学 · 物理学 2025-07-15 Jianwei Qin , Yanbing Liu , Yan Liu , Xun Liu , Wei Li , Fangwei Ye

Deep neural networks (DNNs) have set benchmarks on a wide array of supervised learning tasks. Trained DNNs, however, often lack robustness to minor adversarial perturbations to the input, which undermines their true practicality. Recent…

机器学习 · 计算机科学 2018-11-20 Farzan Farnia , Jesse M. Zhang , David Tse

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the…

神经与进化计算 · 计算机科学 2017-02-28 Joachim Ott , Zhouhan Lin , Ying Zhang , Shih-Chii Liu , Yoshua Bengio
‹ 上一页 1 8 9 10 下一页 ›