paper-with-me

홈 › Papers

FeTa: A DCA Pruning Algorithm with Generalization Error Guarantees

2018-03-12 · Konstantinos Pitas, Mike Davies, Pierre Vandergheynst

Recent DNN pruning algorithms have succeeded in reducing the number of parameters in fully connected layers, often with little or no drop in classification accuracy. However, most of the existing pruning schemes either have to be applied during training or require a costly retraining procedure after pruning to regain classification accuracy. We start by proposing a cheap pruning algorithm for fully connected DNN layers based on difference of convex functions (DC) optimisation, that requires little or no retraining. We then provide a theoretical analysis for the growth in the Generalization Error (GE) of a DNN for the case of bounded perturbations to the hidden layers, of which weight pruning is a special case. Our pruning method is orders of magnitude faster than competing approaches, while our theoretical analysis sheds light to previously observed problems in DNN pruning. Experiments on commnon feedforward neural networks validate our results.

📄 PDF Abstract BibTeX arXiv:1803.04239

Code (1)

konstantinos-p/FeTa_Fully_Connected

Tasks

General Classification

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

FetalDiffusion: Pose-Controllable 3D Fetal MRI Synthesis with Conditional Diffusion Model

2024-03-29 · Molin Zhang, Polina Golland, Patricia Ellen Grant, Elfar Adalsteinsson

The quality of fetal MRI is significantly affected by unpredictable and substantial fetal motion, leading to the introduction of artifacts even when fast acquisition sequences are employed. The development of 3D real-tim…

GPUPose Estimation

Generalization Bounds for Magnitude-Based Pruning via Sparse Matrix Sketching

2023-05-30 · Etash Kumar Guha, Prasanjit Dubey, Xiaoming Huo

In this paper, we derive a novel bound on the generalization error of Magnitude-Based pruning of overparameterized neural networks. Our work builds on the bounds in Arora et al. [2018] where the error depends on one, the…

Generalization Bounds

Enhancing the Regularization Effect of Weight Pruning in Artificial Neural Networks

2018-05-04 · Brian Bartoldson, Adrian Barbu, Gordon Erlebacher

Artificial neural networks (ANNs) may not be worth their computational/memory costs when used in mobile phones or embedded devices. Parameter-pruning algorithms combat these costs, with some algorithms capable of removin…

General Classificationimage-classificationImage Classification

Classification of fetal compromise during labour: signal processing and feature engineering of the cardiotocograph

2021-10-31 · M. O'Sullivan, T. Gabruseva, G. Boylan, M. O'Riordan 외

Cardiotocography (CTG) is the main tool used for fetal monitoring during labour. Interpretation of CTG requires dynamic pattern recognition in real time. It is recognised as a difficult task with high inter- and intra-ob…

BIG-bench Machine LearningFeature Engineering

Fetal Pose Estimation in Volumetric MRI using a 3D Convolution Neural Network

2019-07-10 · Junshen Xu, Molin Zhang, Esra Abaci Turk, Larry Zhang 외

The performance and diagnostic utility of magnetic resonance imaging (MRI) in pregnancy is fundamentally constrained by fetal motion. Motion of the fetus, which is unpredictable and rapid on the scale of conventional ima…

DiagnosticPose EstimationTime SeriesTime Series Analysis