中文
相关论文

相关论文: Robust Learning of Parsimonious Deep Neural Networ…

200 篇论文

We propose an algorithm capable of identifying and eliminating irrelevant layers of a neural network during the early stages of training. In contrast to weight or filter-level pruning, layer pruning reduces the harder to parallelize…

机器学习 · 计算机科学 2024-06-10 Valentin Frank Ingmar Guenter , Athanasios Sideris

We propose a novel algorithm for combined unit and layer pruning of deep neural networks that functions during training and without requiring a pre-trained network to apply. Our algorithm optimally trades-off learning accuracy and pruning…

机器学习 · 计算机科学 2025-07-17 Valentin Frank Ingmar Guenter , Athanasios Sideris

We introduce a pruning algorithm that provably sparsifies the parameters of a trained model in a way that approximately preserves the model's predictive accuracy. Our algorithm uses a small batch of input points to construct a data-informed…

机器学习 · 计算机科学 2021-03-16 Cenk Baykal , Lucas Liebenwein , Igor Gilitschenski , Dan Feldman , Daniela Rus

Modern neural network architectures typically have many millions of parameters and can be pruned significantly without substantial loss in effectiveness which demonstrates they are over-parameterized. The contribution of this work is…

机器学习 · 统计学 2021-03-09 Yaniv Shulman

Pruning neural networks has regained interest in recent years as a means to compress state-of-the-art deep neural networks and enable their deployment on resource-constrained devices. In this paper, we propose a robust compressive learning…

机器学习 · 计算机科学 2020-06-05 George Retsinas , Athena Elafrou , Georgios Goumas , Petros Maragos

The unmatched ability of Deep Neural Networks in capturing complex patterns in large and noisy datasets is often associated with their large hypothesis space, and consequently to the vast amount of parameters that characterize model…

机器学习 · 计算机科学 2026-02-25 Enrico Ballini , Luca Muscarnera , Alessio Fumagalli , Anna Scotti , Francesco Regazzoni

Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently…

神经与进化计算 · 计算机科学 2019-05-28 Xiaoliang Dai , Hongxu Yin , Niraj K. Jha

Deep Neural Networks have been used in a wide variety of applications with significant success. However, their highly complex nature owing to comprising millions of parameters has lead to problems during deployment in pipelines with low…

机器学习 · 计算机科学 2022-08-15 Elvis Johnson , Xiaochen Tang , Sriramacharyulu Samudrala

Deep neural networks have achieved impressive performance in many applications but their large number of parameters lead to significant computational and storage overheads. Several recent works attempt to mitigate these overheads by…

机器学习 · 计算机科学 2019-06-17 Vikash Sehwag , Shiqi Wang , Prateek Mittal , Suman Jana

How to develop slim and accurate deep neural networks has become crucial for real- world applications, especially for those employed in embedded systems. Though previous work along this research line has shown some promising results, most…

神经与进化计算 · 计算机科学 2019-10-02 Xin Dong , Shangyu Chen , Sinno Jialin Pan

Deep Neural Networks are highly over-parameterized and the size of the neural networks can be reduced significantly after training without any decrease in performance. One can clearly see this phenomenon in a wide range of architectures…

机器学习 · 计算机科学 2018-06-19 Utku Evci

In recent years, deep neural networks have known a wide success in various application domains. However, they require important computational and memory resources, which severely hinders their deployment, notably on mobile devices or for…

计算机视觉与模式识别 · 计算机科学 2021-12-16 Nathan Hubens , Matei Mancas , Bernard Gosselin , Marius Preda , Titus Zaharia

Overparameterized Neural Networks (NN) display state-of-the-art performance. However, there is a growing need for smaller, energy-efficient, neural networks tobe able to use machine learning applications on devices with limited…

机器学习 · 统计学 2021-05-21 Soufiane Hayou , Jean-Francois Ton , Arnaud Doucet , Yee Whye Teh

The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. However, existing pruning techniques have one or more of the…

机器学习 · 计算机科学 2020-10-13 Sai Aparna Aketi , Sourjya Roy , Anand Raghunathan , Kaushik Roy

Network pruning reduces the size of neural networks by removing (pruning) neurons such that the performance drop is minimal. Traditional pruning approaches focus on designing metrics to quantify the usefulness of a neuron which is often…

计算机视觉与模式识别 · 计算机科学 2021-11-01 Shehryar Malik , Muhammad Umair Haider , Omer Iqbal , Murtaza Taj

Network pruning is an important research field aiming at reducing computational costs of neural networks. Conventional approaches follow a fixed paradigm which first trains a large and redundant network, and then determines which units…

计算机视觉与模式识别 · 计算机科学 2019-09-30 Yulong Wang , Xiaolu Zhang , Lingxi Xie , Jun Zhou , Hang Su , Bo Zhang , Xiaolin Hu

Deep Neural Networks (DNNs) are usually over-parameterized, causing excessive memory and interconnection cost on the hardware platform. Existing pruning approaches remove secondary parameters at the end of training to reduce the model size;…

机器学习 · 计算机科学 2019-11-12 Gokul Krishnan , Xiaocong Du , Yu Cao

Modern deep networks have millions to billions of parameters, which leads to high memory and energy requirements during training as well as during inference on resource-constrained edge devices. Consequently, pruning techniques have been…

机器学习 · 计算机科学 2020-03-06 Sourjya Roy , Priyadarshini Panda , Gopalakrishnan Srinivasan , Anand Raghunathan

Pruning the weights of randomly initialized neural networks plays an important role in the context of lottery ticket hypothesis. Ramanujan et al. (2020) empirically showed that only pruning the weights can achieve remarkable performance…

机器学习 · 计算机科学 2022-04-06 Daiki Chijiwa , Shin'ya Yamaguchi , Yasutoshi Ida , Kenji Umakoshi , Tomohiro Inoue

Neural network pruning is a highly effective technique aimed at reducing the computational and memory demands of large neural networks. In this research paper, we present a novel approach to pruning neural networks utilizing Bayesian…

机器学习 · 统计学 2023-08-07 Sunil Mathew , Daniel B. Rowe
‹ 上一页 1 2 3 10 下一页 ›