About: A new sensitivity-based pruning technique for feed-forward neural networks that improves generalization

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: A new sensitivity-based pruning technique for feed-forward neural networks that improves generalization Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
Description	Multi-layer neural networks of the back-propagation type (MLP-networks) became a well-established tool used in various application areas. Reliable solutions require, however, also sufficient generalization capabilities of the formed networks and an easy interpretation of their function. These characteristics are strongly related to less sensitive networks with an optimized network structure. In this paper, we will introduce a new pruning technique called SCGSIR that is inspired by the fast method of scaled conjugate gradients (SCG) and sensitivity analysis. Network sensitivity inhibited during training impacts efficient optimization of network structure. Experiments performed so far yield promising results outperforming the reference techniques when considering both their ability to find networks with optimum architecture and improved generalization. Multi-layer neural networks of the back-propagation type (MLP-networks) became a well-established tool used in various application areas. Reliable solutions require, however, also sufficient generalization capabilities of the formed networks and an easy interpretation of their function. These characteristics are strongly related to less sensitive networks with an optimized network structure. In this paper, we will introduce a new pruning technique called SCGSIR that is inspired by the fast method of scaled conjugate gradients (SCG) and sensitivity analysis. Network sensitivity inhibited during training impacts efficient optimization of network structure. Experiments performed so far yield promising results outperforming the reference techniques when considering both their ability to find networks with optimum architecture and improved generalization. (en)
Title	A new sensitivity-based pruning technique for feed-forward neural networks that improves generalization A new sensitivity-based pruning technique for feed-forward neural networks that improves generalization (en)
skos:prefLabel	A new sensitivity-based pruning technique for feed-forward neural networks that improves generalization A new sensitivity-based pruning technique for feed-forward neural networks that improves generalization (en)
skos:notation	RIV/00216208:11320/11:10103633!RIV12-GA0-11320___
http://linked.open...avai/predkladatel	Matematicko-fyzikální fakulta
http://linked.open...avai/riv/aktivita	P Z
http://linked.open...avai/riv/aktivity	P(GAP103/10/0783), P(GAP202/10/1333), P(GD201/09/H057), Z(MSM0021620838)
http://linked.open...vai/riv/dodaniDat	2012
http://linked.open...aciTvurceVysledku	Mrázová, Iveta Reitermanová, Zuzana
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	Univerzita Karlova v Praze / Matematicko-fyzikální fakulta
http://linked.open...dnocenehoVysledku	183969
http://linked.open...ai/riv/idVysledku	RIV/00216208:11320/11:10103633
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	feed-forward neural networks; pruning; sensitivity; generalization (en)
http://linked.open.../riv/klicoveSlovo	feed-forward neural networks generalization pruning sensitivity
http://linked.open...ontrolniKodProRIV	[9AB55E6A33B5]
http://linked.open...v/mistoKonaniAkce	San Jose, USA
http://linked.open...i/riv/mistoVydani	Piscataway, NJ, USA
http://linked.open...i/riv/nazevZdroje	Proceedings of The 2011 International Joint Conference on Neural Networks (IJCNN)
http://linked.open...in/vavai/riv/obor	BD
http://linked.open...ichTvurcuVysledku	2 (xsd:int)
http://linked.open...cetTvurcuVysledku	2 (xsd:int)
http://linked.open...vavai/riv/projekt	NoSCoM: Non-Standard Computational Models and Their Applications in Complexity, Linguistics, and Learning Res Informatica Structure and its impact for recognition
http://linked.open...UplatneniVysledku	2011
http://linked.open...iv/tvurceVysledku	Mrázová, Iveta Reitermanová, Zuzana
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2011-07-31 (xsd:date)
http://linked.open...n/vavai/riv/zamer	Moderní metody, struktury a systémy informatiky
issn	2161-4393
number of pages	8 (xsd:int)
http://bibframe.org/vocab/doi	10.1109/IJCNN.2011.6033493
http://purl.org/ne...btex#hasPublisher	IEEE
https://schema.org/isbn	978-1-4244-9635-8
http://localhost/t...ganizacniJednotka	11320
is http://linked.open...avai/riv/vysledek of	A new sensitivity-based pruning technique for feed-forward neural networks that improves generalization A new sensitivity-based pruning technique for feed-forward neural networks that improves generalization

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software