中文
相关论文

相关论文: Lost in Pruning: The Effects of Pruning Neural Net…

200 篇论文

Reducing the size of a neural network (pruning) by removing weights without impacting its performance is an important problem for resource-constrained devices. In the past, pruning was typically accomplished by ranking or penalizing weights…

机器学习 · 计算机科学 2023-08-22 Rajan Sahu , Shivam Chadha , Nithin Nagaraj , Archana Mathur , Snehanshu Saha

Modern deep neural networks require a significant amount of computing time and power to train and deploy, which limits their usage on edge devices. Inspired by the iterative weight pruning in the Lottery Ticket Hypothesis, we propose…

机器学习 · 计算机科学 2022-07-15 John Tan Chong Min , Mehul Motani

Convolutional neural networks (CNN) play a major role in image processing tasks like image classification, object detection, semantic segmentation. Very often CNN networks have from several to hundred stacked layers with several megabytes…

机器学习 · 计算机科学 2020-02-18 Marcin Pietron , Maciej Wielgosz

The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, able to perform more efficiently in resource-constrained…

计算机视觉与模式识别 · 计算机科学 2023-03-21 Nathan Hubens , Victor Delvigne , Matei Mancas , Bernard Gosselin , Marius Preda , Titus Zaharia

Pruning is a well-established technique for removing unnecessary structure from neural networks after training to improve the performance of inference. Several recent results have explored the possibility of pruning at initialization time…

机器学习 · 计算机科学 2020-09-29 Jonathan Frankle , Gintare Karolina Dziugaite , Daniel M. Roy , Michael Carbin

Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the…

机器学习 · 计算机科学 2023-09-11 Denis Kuznedelev , Eldar Kurtic , Eugenia Iofinova , Elias Frantar , Alexandra Peste , Dan Alistarh

Recent work has highlighted the complex influence training hyperparameters, e.g., the number of training epochs, can have on the prunability of machine learning models. Perhaps surprisingly, a systematic approach to predict precisely how…

机器学习 · 统计学 2024-03-04 Yefan Zhou , Yaoqing Yang , Arin Chang , Michael W. Mahoney

State-of-the-art deep learning models have a parameter count that reaches into the billions. Training, storing and transferring such models is energy and time consuming, thus costly. A big part of these costs is caused by training the…

机器学习 · 计算机科学 2023-05-26 Paul Wimmer , Jens Mehnert , Alexandru Paul Condurache

Deep Neural Networks (DNNs) are often over-parameterized for their tasks and can be compressed quite drastically by removing weights, a process called pruning. We investigate the impact of different pruning techniques on the classification…

机器学习 · 计算机科学 2026-05-26 Jonathan von Rad , Florian Seuffert

We present a filter pruning approach for deep model compression, using a multitask network. Our approach is based on learning a a pruner network to prune a pre-trained target network. The pruner is essentially a multitask deep neural…

计算机视觉与模式识别 · 计算机科学 2020-01-17 Vinay Kumar Verma , Pravendra Singh , Vinay P. Namboodiri , Piyush Rai

Deep learning harnesses massive parallel floating-point processing to train and evaluate large neural networks. Trends indicate that deeper and larger neural networks with an increasing number of parameters achieve higher accuracy than…

计算机视觉与模式识别 · 计算机科学 2023-08-29 Brad Larson , Bishal Upadhyaya , Luke McDermott , Siddha Ganju

Pruning neural networks, i.e., removing some of their parameters whilst retaining their accuracy, is one of the main ways to reduce the latency of a machine learning pipeline, especially in resource- and/or bandwidth-constrained scenarios.…

机器学习 · 计算机科学 2025-03-28 Carla Fabiana Chiasserini , Francesco Malandrino , Nuria Molner , Zhiqiang Zhao

While task-specific finetuning of pretrained networks has led to significant empirical advances in NLP, the large size of networks makes finetuning difficult to deploy in multi-task, memory-constrained settings. We propose diff pruning as a…

计算与语言 · 计算机科学 2021-06-10 Demi Guo , Alexander M. Rush , Yoon Kim

We explore the applications of random matrix theory (RMT) in the training of deep neural networks (DNNs), focusing on layer pruning that is reducing the number of DNN parameters (weights). Our numerical results show that this pruning leads…

机器学习 · 计算机科学 2024-09-10 Leonid Berlyand , Etienne Sandier , Yitzchak Shmalo , Lei Zhang

In Machine Learning, Artificial Neural Networks (ANNs) are a very powerful tool, broadly used in many applications. Often, the selected (deep) architectures include many layers, and therefore a large amount of parameters, which makes…

机器学习 · 计算机科学 2022-06-29 Matteo Cacciola , Antonio Frangioni , Xinlin Li , Andrea Lodi

Deep neural networks have been applied in many applications exhibiting extraordinary abilities in the field of computer vision. However, complex network architectures challenge efficient real-time deployment and require significant…

计算机视觉与模式识别 · 计算机科学 2021-06-16 Tailin Liang , John Glossner , Lei Wang , Shaobo Shi , Xiaotong Zhang

We surely enjoy the larger the better models for their superior performance in the last couple of years when both the hardware and software support the birth of such extremely huge models. The applied fields include text mining and others.…

计算与语言 · 计算机科学 2024-06-04 Hanjuan Huang , Hao-Jia Song , Hsing-Kuo Pao

The remarkable performance of deep Convolutional neural networks (CNNs) is generally attributed to their deeper and wider architectures, which can come with significant computational costs. Pruning neural networks has thus gained interest…

计算机视觉与模式识别 · 计算机科学 2023-12-01 Yang He , Lingao Xiao

Deep learning stands as the modern paradigm for solving cognitive tasks. However, as the problem complexity increases, models grow deeper and computationally prohibitive, hindering advancements in real-world and resource-constrained…

计算机视觉与模式识别 · 计算机科学 2025-06-06 Gustavo Henrique do Nascimento , Ian Pons , Anna Helena Reali Costa , Artur Jordao

Deep Reinforcement Learning (RL) is a powerful framework for solving complex real-world problems. Large neural networks employed in the framework are traditionally associated with better generalization capabilities, but their increased size…

机器学习 · 计算机科学 2022-01-03 Samin Yeasar Arnob , Riyasat Ohib , Sergey Plis , Doina Precup