Pruning algorithms of neural networks — a comparative study
Abstract: The neural network with optimal architecture speeds up the learning process and generalizes the problem well for further knowledge extraction. As a result researchers have developed various techniques for pruning the neural networks. This paper provides a survey of existing pruning techniques that optimize the architecture of neural networks and discusses their advantages and limitations. Also the paper evaluates the effectiveness of various pruning techniques by comparing the performance of some traditional and recent pruning algorithms based on sensitivity analysis, mutual information and significance on four real datasets namely Iris, Wisconsin breast cancer, Hepatitis Domain and Pima Indian Diabetes.
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Erschienen in
-
Pruning algorithms of neural networks — a comparative study ; volume:3 ; number:3 ; year:2013 ; pages:105-115 ; extent:11
Open computer science ; 3, Heft 3 (2013), 105-115 (gesamt 11)
- Urheber
-
Augasta, M.
Kathirvalavakumar, T.
- DOI
-
10.2478/s13537-013-0109-x
- URN
-
urn:nbn:de:101:1-2410301518427.779247332220
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
- 15.08.2025, 07:30 MESZ
Datenpartner
Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Augasta, M.
- Kathirvalavakumar, T.
Ähnliche Objekte (12)
Pruning and quantization for efficient deep neural networks
Least-squares based layerwise pruning of Deep Neural Networks
Novel clustering-based pruning algorithms
Hardware-Aware Evolutionary Explainable Filter Pruning for Convolutional Neural Networks
Complex hybrid weighted pruning method for accelerating convolutional neural networks
Recursive least squares method for training and pruning convolutional neural networks
A roulette wheel-based pruning method to simplify cumbersome deep neural networks
Learning algorithms in artificial neural networks
A Novel Attention‐Based Layer Pruning Approach for Low‐Complexity Convolutional Neural Networks
An efficient pruning scheme of deep neural networks for Internet of Things applications
Differentiable channel pruning guided via attention mechanism: a novel neural network pruning approach
Pruning
Pruning and quantization for efficient deep neural networks
Least-squares based layerwise pruning of Deep Neural Networks
Novel clustering-based pruning algorithms
Hardware-Aware Evolutionary Explainable Filter Pruning for Convolutional Neural Networks
Complex hybrid weighted pruning method for accelerating convolutional neural networks
Recursive least squares method for training and pruning convolutional neural networks
A roulette wheel-based pruning method to simplify cumbersome deep neural networks
Learning algorithms in artificial neural networks
A Novel Attention‐Based Layer Pruning Approach for Low‐Complexity Convolutional Neural Networks
An efficient pruning scheme of deep neural networks for Internet of Things applications
Differentiable channel pruning guided via attention mechanism: a novel neural network pruning approach
Pruning
Pruning and quantization for efficient deep neural networks
Least-squares based layerwise pruning of Deep Neural Networks
Novel clustering-based pruning algorithms
Hardware-Aware Evolutionary Explainable Filter Pruning for Convolutional Neural Networks
Complex hybrid weighted pruning method for accelerating convolutional neural networks
Recursive least squares method for training and pruning convolutional neural networks
A roulette wheel-based pruning method to simplify cumbersome deep neural networks
Learning algorithms in artificial neural networks
A Novel Attention‐Based Layer Pruning Approach for Low‐Complexity Convolutional Neural Networks
An efficient pruning scheme of deep neural networks for Internet of Things applications
Differentiable channel pruning guided via attention mechanism: a novel neural network pruning approach