中文
相关论文

相关论文: Tensor Yard: One-Shot Algorithm of Hardware-Friend…

200 篇论文

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks…

计算机视觉与模式识别 · 计算机科学 2018-05-15 Yi-Min Chou , Yi-Ming Chan , Jia-Hong Lee , Chih-Yi Chiu , Chu-Song Chen

Deep neural networks have been one of the dominant machine learning approaches in recent years. Several new network structures are proposed and have better performance than the traditional feedforward neural network structure.…

计算机视觉与模式识别 · 计算机科学 2018-10-04 Huan Li , Yibo Yang , Dongmin Chen , Zhouchen Lin

This paper aims to accelerate the test-time computation of convolutional neural networks (CNNs), especially very deep CNNs that have substantially impacted the computer vision community. Unlike previous methods that are designed for…

计算机视觉与模式识别 · 计算机科学 2015-11-19 Xiangyu Zhang , Jianhua Zou , Kaiming He , Jian Sun

In recent years deep learning algorithms have shown extremely high performance on machine learning tasks such as image classification and speech recognition. In support of such applications, various FPGA accelerator architectures have been…

机器学习 · 计算机科学 2017-05-09 Xinyu Zhang , Srinjoy Das , Ojash Neopane , Ken Kreutz-Delgado

With the general trend of increasing Convolutional Neural Network (CNN) model sizes, model compression and acceleration techniques have become critical for the deployment of these models on edge devices. In this paper, we provide a…

机器学习 · 计算机科学 2020-05-12 Jiayi Liu , Samarth Tripathi , Unmesh Kurup , Mohak Shah

Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity and…

机器学习 · 计算机科学 2019-01-01 Ghouthi Boukli Hacene , Vincent Gripon , Matthieu Arzel , Nicolas Farrugia , Yoshua Bengio

This paper is on improving the training of binary neural networks in which both activations and weights are binary. While prior methods for neural network binarization binarize each filter independently, we propose to instead parametrize…

计算机视觉与模式识别 · 计算机科学 2019-04-17 Adrian Bulat , Jean Kossaifi , Georgios Tzimiropoulos , Maja Pantic

In this paper, we describe a phenomenon, which we named "super-convergence", where neural networks can be trained an order of magnitude faster than with standard training methods. The existence of super-convergence is relevant to…

机器学习 · 计算机科学 2018-05-18 Leslie N. Smith , Nicholay Topin

We introduce compositional tensor trains (CTTs) for the approximation of multivariate functions, a class of models obtained by composing low-rank functions in the tensor-train format. This format can encode standard approximation tools,…

数值分析 · 数学 2025-12-23 Martin Eigel , Charles Miranda , Anthony Nouy , David Sommer

This paper is focused on the improvement the efficiency of the sparse convolutional neural networks (CNNs) layers on graphic processing units (GPU). The Nvidia deep neural network (cuDnn) library provides the most effective implementation…

机器学习 · 计算机科学 2022-01-03 Marcin Pietroń , Dominik Żurek

Convolutional neural networks have achieved great success in various vision tasks; however, they incur heavy resource costs. By using deeper and wider networks, network accuracy can be improved rapidly. However, in an environment with…

计算机视觉与模式识别 · 计算机科学 2018-11-01 Yunho Jeon , Junmo Kim

In this paper, we propose a novel optimization algorithm for training machine learning models called Input Normalized Stochastic Gradient Descent (INSGD), inspired by the Normalized Least Mean Squares (NLMS) algorithm used in adaptive…

机器学习 · 计算机科学 2023-06-28 Salih Atici , Hongyi Pan , Ahmet Enis Cetin

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

机器学习 · 计算机科学 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

Recent studies have used deep residual convolutional neural networks (CNNs) for JPEG compression artifact reduction. This study proposes a scalable CNN called S-Net. Our approach effectively adjusts the network scale dynamically in a…

计算机视觉与模式识别 · 计算机科学 2019-07-24 Bolun Zheng , Rui Sun , Xiang Tian , Yaowu Chen

Convolutional neural networks have achieved a great success in the recent years. Although, the way to maximize the performance of the convolutional neural networks still in the beginning. Furthermore, the optimization of the size and the…

计算机视觉与模式识别 · 计算机科学 2017-06-21 Hussam Qassim , David Feinzimer , Abhishek Verma

This chapter studies the problem of decomposing a tensor into a sum of constituent rank one tensors. While tensor decompositions are very useful in designing learning algorithms and data analysis, they are NP-hard in the worst-case. We will…

数据结构与算法 · 计算机科学 2020-07-31 Aravindan Vijayaraghavan

Deep Neural Networks (DNNs) have achieved im- pressive accuracy in many application domains including im- age classification. Training of DNNs is an extremely compute- intensive process and is solved using variants of the stochastic…

分布式、并行与集群计算 · 计算机科学 2017-11-03 Sameer Kumar , Dheeraj Sreedhar , Vaibhav Saxena , Yogish Sabharwal , Ashish Verma

State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights. Training these models is very compute- and memory-resource intensive. Much research has been done on pruning or…

机器学习 · 计算机科学 2019-12-10 Sangkug Lym , Esha Choukse , Siavash Zangeneh , Wei Wen , Sujay Sanghavi , Mattan Erez

Despite the remarkable performance, modern deep neural networks are inevitably accompanied by a significant amount of computational cost for learning and deployment, which may be incompatible with their usage on edge devices. Recent efforts…

计算机视觉与模式识别 · 计算机科学 2022-03-11 Seul-Ki Yeom , Kyung-Hwan Shim , Jee-Hyun Hwang

Deep neural networks have been used in various machine learning applications and achieved tremendous empirical successes. However, training deep neural networks is a challenging task. Many alternatives have been proposed in place of…

机器学习 · 计算机科学 2020-09-09 Yeonjong Shin
‹ 上一页 1 8 9 10 下一页 ›