中文
相关论文

相关论文: Safety-Oriented Pruning and Interpretation of Rein…

200 篇论文

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

Recent advancements have scaled neural networks to unprecedented sizes, achieving remarkable performance across a wide range of tasks. However, deploying these large-scale models on resource-constrained devices poses significant challenges…

机器学习 · 计算机科学 2024-10-22 Mostafa Hussien , Mahmoud Afifi , Kim Khoa Nguyen , Mohamed Cheriet

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

One of the major challenges in deploying deep neural network architectures is their size which has an adverse effect on their inference time and memory requirements. Deep CNNs can either be pruned width-wise by removing filters based on…

计算机视觉与模式识别 · 计算机科学 2020-10-07 Muhammad Umair Haider , Murtaza Taj

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the…

Reinforcement learning policies are typically represented by black-box neural networks, which are non-interpretable and not well-suited for safety-critical domains. To address both of these issues, we propose constrained normalizing flow…

机器学习 · 计算机科学 2024-05-03 Finn Rietz , Erik Schaffernicht , Stefan Heinrich , Johannes A. Stork

Pruning methods have shown to be effective at reducing the size of deep neural networks while keeping accuracy almost intact. Among the most effective methods are those that prune a network while training it with a sparsity prior loss and…

神经与进化计算 · 计算机科学 2019-12-20 Carl Lemaire , Andrew Achkar , Pierre-Marc Jodoin

Neural Networks (NNs) have increasingly apparent safety implications commensurate with their proliferation in real-world applications: both unanticipated as well as adversarial misclassifications can result in fatal outcomes. As a…

机器学习 · 计算机科学 2021-04-20 Haitham Khedr , James Ferlez , Yasser Shoukry

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

Understanding and shaping the behaviour of Large Language Models (LLMs) is increasingly important as applications become more powerful and more frequently adopted. This paper introduces a machine unlearning method specifically designed for…

机器学习 · 计算机科学 2024-07-25 Nicholas Pochinkov , Nandi Schoots

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

Structural model pruning is a prominent approach used for reducing the computational cost of Convolutional Neural Networks (CNNs) before their deployment on resource-constrained devices. Yet, the majority of proposed ideas require a…

计算机视觉与模式识别 · 计算机科学 2024-03-29 Alireza Ganjdanesh , Shangqian Gao , Heng Huang

Vision Transformer and its variants have been adopted in many visual tasks due to their powerful capabilities, which also bring significant challenges in computation and storage. Consequently, researchers have introduced various compression…

神经与进化计算 · 计算机科学 2024-07-30 Zeyu Wang , Weichen Dai , Xiangyu Zhou , Ji Qi , Yi Zhou

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

Neural networks grow vastly in size to tackle more sophisticated tasks. In many cases, such large networks are not deployable on particular hardware and need to be reduced in size. Pruning techniques help to shrink deep neural networks to…

机器学习 · 计算机科学 2022-06-01 Udo Schlegel , Samuel Schiegg , Daniel A. Keim

Scope of reproducibility: We are reproducing Comparing Rewinding and Fine-tuning in Neural Networks from arXiv:2003.02389. In this work the authors compare three different approaches to retraining neural networks after pruning: 1)…

机器学习 · 计算机科学 2021-09-22 Szymon Mikler

Over the last century, deep learning models have become the state-of-the-art for solving complex computer vision problems. These modern computer vision models have millions of parameters, which presents two major challenges: (1) the…

计算机视觉与模式识别 · 计算机科学 2025-01-15 Florian Merkle , David Weber , Pascal Schöttle , Stephan Schlögl , Martin Nocker

Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most existing research focuses primarily on balancing the sparsity and…

密码学与安全 · 计算机科学 2022-08-05 Xiaoyong Yuan , Lan Zhang

Convolutional Neural Networks (CNNs) compression is crucial to deploying these models in edge devices with limited resources. Existing channel pruning algorithms for CNNs have achieved plenty of success on complex models. They approach the…

计算机视觉与模式识别 · 计算机科学 2022-09-08 Alireza Ganjdanesh , Shangqian Gao , Heng Huang

Convolutional neural networks (CNNs) have demonstrated extraordinarily good performance in many computer vision tasks. The increasing size of CNN models, however, prevents them from being widely deployed to devices with limited…

计算机视觉与模式识别 · 计算机科学 2020-09-22 Guan Li , Junpeng Wang , Han-Wei Shen , Kaixin Chen , Guihua Shan , Zhonghua Lu