中文
相关论文

相关论文: The Effects of Approximate Multiplication on Convo…

200 篇论文

We present an approximation algorithm that takes a pool of pre-trained models as input and produces from it a cascaded model with similar accuracy but lower average-case cost. Applied to state-of-the-art ImageNet classification models, this…

机器学习 · 计算机科学 2018-02-22 Matthew Streeter

We present a new method to approximate posterior probabilities of Bayesian Network using Deep Neural Network. Experiment results on several public Bayesian Network datasets shows that Deep Neural Network is capable of learning joint…

机器学习 · 计算机科学 2018-01-12 Jie Jia , Honggang Zhou , Yunchun Li

Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a…

机器学习 · 计算机科学 2018-02-06 Jianbo Ye , Xin Lu , Zhe Lin , James Z. Wang

Convolutional Neural Networks (CNNs) reach high accuracies in various application domains, but require large amounts of computation and incur costly data movements. One method to decrease these costs while trading accuracy is weight and/or…

硬件体系结构 · 计算机科学 2022-08-10 Cecilia Latotzke , Tim Ciesielski , Tobias Gemmeke

Channel pruning is a promising technique to compress the parameters of deep convolutional neural networks(DCNN) and to speed up the inference. This paper aims to address the long-standing inefficiency of channel pruning. Most channel…

计算机视觉与模式识别 · 计算机科学 2021-09-01 Zhouyang Xie , Yan Fu , Shengzhao Tian , Junlin Zhou , Duanbing Chen

We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root. This allows a significant reduction in computational cost…

神经与进化计算 · 计算机科学 2020-10-13 Yani Ioannou , Duncan Robertson , Roberto Cipolla , Antonio Criminisi

Multiplications are responsible for most of the computational cost involved in neural network training and inference. Recent research has thus looked for ways to reduce the cost associated with them. Inspired by Mogami (2020), we replace…

机器学习 · 计算机科学 2023-10-26 Atli Kosson , Martin Jaggi

The deployment of deep convolutional neural networks (CNNs) in many real world applications is largely hindered by their high computational cost. In this paper, we propose a novel learning scheme for CNNs to simultaneously 1) reduce the…

计算机视觉与模式识别 · 计算机科学 2017-08-23 Zhuang Liu , Jianguo Li , Zhiqiang Shen , Gao Huang , Shoumeng Yan , Changshui Zhang

Deep Neural Networks (DNNs) rely heavily on dense arithmetic operations, motivating the use of Approximate Multipliers (AxMs) to reduce energy consumption in hardware accelerators. However, a rigorous mathematical characterization of how…

硬件体系结构 · 计算机科学 2025-12-09 A. M. H. H. Alahakoon , Hassaan Saadat , Darshana Jayasinghe , Sri Parameswaran

Approximate computing is known for enhancing deep neural network accelerators' energy efficiency by introducing inexactness with a tolerable accuracy loss. However, small accuracy variations may increase the sensitivity of these…

硬件体系结构 · 计算机科学 2023-02-23 Ayesha Siddique , Khaza Anuarul Hoque

Rational and neural network based approximations are efficient tools in modern approximation. These approaches are able to produce accurate approximations to nonsmooth and non-Lipschitz functions, including multivariate domain functions. In…

最优化与控制 · 数学 2023-09-08 Vinesha Peiris , Reinier Diaz Millan , Nadezda Sukhorukova , Julien Ugon

The design and implementation of Deep Learning (DL) models is currently receiving a lot of attention from both industrials and academics. However, the computational workload associated with DL is often out of reach for low-power embedded…

硬件体系结构 · 计算机科学 2022-12-09 Etienne Dupuis , Silviu-Ioan Filip , Olivier Sentieys , David Novo , Ian O'Connor , Alberto Bosio

Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern when seeking to deploy very deep architectures in production,…

机器学习 · 计算机科学 2019-10-30 Ayan Chakrabarti , Benjamin Moseley

Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations. The key idea is to rank the filters based on a certain criterion (say, $l_1$-norm, average…

计算机视觉与模式识别 · 计算机科学 2018-02-01 Deepak Mittal , Shweta Bhardwaj , Mitesh M. Khapra , Balaraman Ravindran

Recent advances in Capsule Networks (CapsNets) have shown their superior learning capability, compared to the traditional Convolutional Neural Networks (CNNs). However, the extremely high complexity of CapsNets limits their fast deployment…

机器学习 · 计算机科学 2020-07-03 Alberto Marchisio , Vojtech Mrazek , Muhammad Abudllah Hanif , Muhammad Shafique

The growth in the complexity of Convolutional Neural Networks (CNNs) is increasing interest in partitioning a network across multiple accelerators during training and pipelining the backpropagation computations over the accelerators.…

分布式、并行与集群计算 · 计算机科学 2020-01-01 Lifu Zhang , Tarek S. Abdelrahman

The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create…

机器学习 · 计算机科学 2021-04-13 Zongwei Zhou , Jae Y. Shin , Suryakanth R. Gurudu , Michael B. Gotway , Jianming Liang

We study approximation and learning capacities of convolutional neural networks (CNNs) with one-side zero-padding and multiple channels. Our first result proves a new approximation bound for CNNs with certain constraint on the weights. Our…

机器学习 · 计算机科学 2025-07-29 Yunfei Yang , Han Feng , Ding-Xuan Zhou

Convolutional Neural Networks (CNNs) filter the input data using a series of spatial convolution operators with compactly supported stencils and point-wise nonlinearities. Commonly, the convolution operators couple features from all…

数值分析 · 计算机科学 2018-10-04 Eran Treister , Lars Ruthotto , Michal Sharoni , Sapir Zafrani , Eldad Haber

Deep convolutional neural networks contain tens of millions of parameters, making them impossible to work efficiently on embedded devices. We propose iterative approach of applying low-rank approximation to compress deep convolutional…

计算机视觉与模式识别 · 计算机科学 2019-11-18 Maksym Kholiavchenko