English
Related papers

Related papers: Unveiling Invariances via Neural Network Pruning

200 papers

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…

Machine Learning · Computer Science 2020-02-18 Marcin Pietron , Maciej Wielgosz

Invariances in neural networks are useful and necessary for many tasks. However, the representation of the invariance of most neural network models has not been characterized. We propose measures to quantify the invariance of neural…

Machine Learning · Computer Science 2023-10-27 Facundo Manuel Quiroga , Jordina Torrents-Barrena , Laura Cristina Lanzarini , Domenec Puig-Valls

Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value. The current work focuses on fine-grained pruning, which uses…

Machine Learning · Computer Science 2022-09-28 Xiatao Kang , Ping Li , Jiayi Yao , Chengxi Li

We propose a new gradient-based approach for extracting sub-architectures from a given large model. Contrarily to existing pruning methods, which are unable to disentangle the network architecture and the corresponding weights, our…

Machine Learning · Computer Science 2021-07-08 Nicolo Colombo , Yang Gao

We introduce and analyze a new technique for model reduction for deep neural networks. While large networks are theoretically capable of learning arbitrarily complex models, overfitting and model redundancy negatively affects the prediction…

Machine Learning · Computer Science 2017-11-27 Alireza Aghasi , Afshin Abdi , Nam Nguyen , Justin Romberg

We show that the error of iteratively magnitude-pruned networks empirically follows a scaling law with interpretable coefficients that depend on the architecture and task. We functionally approximate the error of the pruned networks,…

Machine Learning · Computer Science 2021-07-06 Jonathan S. Rosenfeld , Jonathan Frankle , Michael Carbin , Nir Shavit

Despite the importance of image representations such as histograms of oriented gradients and deep Convolutional Neural Networks (CNN), our theoretical understanding of them remains limited. Aiming at filling this gap, we investigate three…

Computer Vision and Pattern Recognition · Computer Science 2015-06-23 Karel Lenc , Andrea Vedaldi

Feature extraction with convolutional neural networks (CNNs) is a popular method to represent images for machine learning tasks. These representations seek to capture global image content, and ideally should be independent of geometric…

Machine Learning · Computer Science 2022-03-03 Jake Lee , Junfeng Yang , Zhangyang Wang

Deep learning has arguably achieved tremendous success in recent years. In simple words, deep learning uses the composition of many nonlinear functions to model the complex dependency between input features and labels. While neural networks…

Machine Learning · Statistics 2019-04-16 Jianqing Fan , Cong Ma , Yiqiao Zhong

Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of the learned representation, and that stacking layers and…

Machine Learning · Computer Science 2018-06-29 Alessandro Achille , Stefano Soatto

Many applications require robustness, or ideally invariance, of neural networks to certain transformations of input data. Most commonly, this requirement is addressed by training data augmentation, using adversarial training, or defining…

Computer Vision and Pattern Recognition · Computer Science 2022-09-27 Kanchana Vaishnavi Gandikota , Jonas Geiping , Zorah Lähner , Adam Czapliński , Michael Moeller

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…

Machine Learning · Computer Science 2022-07-15 John Tan Chong Min , Mehul Motani

In this paper we present a new strategy to model the subgrid-scale scalar flux in a three-dimensional turbulent incompressible flow using physics-informed neural networks (NNs). When trained from direct numerical simulation (DNS) data,…

Fluid Dynamics · Physics 2021-03-03 Hugo Frezat , Guillaume Balarac , Julien Le Sommer , Ronan Fablet , Redouane Lguensat

In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Zechun Liu , Haoyuan Mu , Xiangyu Zhang , Zichao Guo , Xin Yang , Tim Kwang-Ting Cheng , Jian Sun

The performance of machine learning models is determined by the quality of their learned features. They should be invariant under irrelevant data variation but sensitive to task-relevant details. To visualize whether this is the case, we…

Machine Learning · Computer Science 2026-03-24 Armand Rousselot , Joran Wendebourg , Ullrich Köthe

Structured pruning is a popular method to reduce the cost of convolutional neural networks, that are the state of the art in many computer vision tasks. However, depending on the architecture, pruning introduces dimensional discrepancies…

Neural and Evolutionary Computing · Computer Science 2022-12-13 Hugo Tessier , Vincent Gripon , Mathieu Léonardon , Matthieu Arzel , David Bertrand , Thomas Hannagan

Pruning - that is, setting a significant subset of the parameters of a neural network to zero - is one of the most popular methods of model compression. Yet, several recent works have raised the issue that pruning may induce or exacerbate…

Computer Vision and Pattern Recognition · Computer Science 2023-04-26 Eugenia Iofinova , Alexandra Peste , Dan Alistarh

We explain equivariant neural networks, a notion underlying breakthroughs in machine learning from deep convolutional neural networks for computer vision to AlphaFold 2 for protein structure prediction, without assuming knowledge of…

Machine Learning · Computer Science 2022-11-18 Lek-Heng Lim , Bradley J. Nelson

We introduce provenance networks, a novel class of neural models designed to provide end-to-end, training-data-driven explainability. Unlike conventional post-hoc methods, provenance networks learn to link each prediction directly to its…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Ali Kayyam , Anusha Madan Gopal , M. Anthony Lewis

Deep neural networks have achieved great success in the last decade. When designing neural networks to handle the ubiquitous geometric data such as point clouds and graphs, it is critical that the model can maintain invariance towards…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Ziwei Zhang , Xin Wang , Zeyang Zhang , Peng Cui , Wenwu Zhu
‹ Prev 1 4 5 6 7 8 10 Next ›