Matches in SemOpenAlex for { <https://semopenalex.org/work/W2017643118> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2017643118 abstract "Multilayer perceptrons (MLP) have been widely applied to pattern recognition. It is found that when the data has a multi-modal distribution, a standard MLP is apt to local minima and a valid neural net classifier is difficult to obtain. In this paper, we propose a two-phase learning modular (TLM) neural net architecture to tackle the local minimum problem. The basic idea is to transform the multi- modal distribution into a known and more learnable distribution before using a global MLP to classify the data. We applied the TLM to the inverse synthetic aperture radar (ISAR) automatic target recognition (ATR), and compared its performance with that of the MLP. Experiments show that the MLP's learning often leads to a fatal minimum if its net size or the initial point is not chosen properly. Its performance depends strongly on the number of training samples as well as the architecture parameters. On the other hand, the TLM is much easier to train and can yield good recognition accuracy, at least comparable to that of the MLP. In addition, the TLM's performance is more robust." @default.
- W2017643118 created "2016-06-24" @default.
- W2017643118 creator A5009052681 @default.
- W2017643118 creator A5019345566 @default.
- W2017643118 date "1996-06-14" @default.
- W2017643118 modified "2023-09-23" @default.
- W2017643118 title "<title>Modular neural net architecture for automatic target recognition</title>" @default.
- W2017643118 doi "https://doi.org/10.1117/12.243158" @default.
- W2017643118 hasPublicationYear "1996" @default.
- W2017643118 type Work @default.
- W2017643118 sameAs 2017643118 @default.
- W2017643118 citedByCount "1" @default.
- W2017643118 crossrefType "proceedings-article" @default.
- W2017643118 hasAuthorship W2017643118A5009052681 @default.
- W2017643118 hasAuthorship W2017643118A5019345566 @default.
- W2017643118 hasConcept C101468663 @default.
- W2017643118 hasConcept C111919701 @default.
- W2017643118 hasConcept C11413529 @default.
- W2017643118 hasConcept C117623542 @default.
- W2017643118 hasConcept C134306372 @default.
- W2017643118 hasConcept C153180895 @default.
- W2017643118 hasConcept C154945302 @default.
- W2017643118 hasConcept C155032097 @default.
- W2017643118 hasConcept C179717631 @default.
- W2017643118 hasConcept C185592680 @default.
- W2017643118 hasConcept C186633575 @default.
- W2017643118 hasConcept C188027245 @default.
- W2017643118 hasConcept C33923547 @default.
- W2017643118 hasConcept C41008148 @default.
- W2017643118 hasConcept C50644808 @default.
- W2017643118 hasConcept C60908668 @default.
- W2017643118 hasConcept C71139939 @default.
- W2017643118 hasConcept C81363708 @default.
- W2017643118 hasConcept C87360688 @default.
- W2017643118 hasConcept C95623464 @default.
- W2017643118 hasConceptScore W2017643118C101468663 @default.
- W2017643118 hasConceptScore W2017643118C111919701 @default.
- W2017643118 hasConceptScore W2017643118C11413529 @default.
- W2017643118 hasConceptScore W2017643118C117623542 @default.
- W2017643118 hasConceptScore W2017643118C134306372 @default.
- W2017643118 hasConceptScore W2017643118C153180895 @default.
- W2017643118 hasConceptScore W2017643118C154945302 @default.
- W2017643118 hasConceptScore W2017643118C155032097 @default.
- W2017643118 hasConceptScore W2017643118C179717631 @default.
- W2017643118 hasConceptScore W2017643118C185592680 @default.
- W2017643118 hasConceptScore W2017643118C186633575 @default.
- W2017643118 hasConceptScore W2017643118C188027245 @default.
- W2017643118 hasConceptScore W2017643118C33923547 @default.
- W2017643118 hasConceptScore W2017643118C41008148 @default.
- W2017643118 hasConceptScore W2017643118C50644808 @default.
- W2017643118 hasConceptScore W2017643118C60908668 @default.
- W2017643118 hasConceptScore W2017643118C71139939 @default.
- W2017643118 hasConceptScore W2017643118C81363708 @default.
- W2017643118 hasConceptScore W2017643118C87360688 @default.
- W2017643118 hasConceptScore W2017643118C95623464 @default.
- W2017643118 hasLocation W20176431181 @default.
- W2017643118 hasOpenAccess W2017643118 @default.
- W2017643118 hasPrimaryLocation W20176431181 @default.
- W2017643118 hasRelatedWork W1992825654 @default.
- W2017643118 hasRelatedWork W2071548362 @default.
- W2017643118 hasRelatedWork W2086630192 @default.
- W2017643118 hasRelatedWork W2161649813 @default.
- W2017643118 hasRelatedWork W2282259862 @default.
- W2017643118 hasRelatedWork W2380451229 @default.
- W2017643118 hasRelatedWork W2612087409 @default.
- W2017643118 hasRelatedWork W2980485553 @default.
- W2017643118 hasRelatedWork W3193301557 @default.
- W2017643118 hasRelatedWork W2179998186 @default.
- W2017643118 isParatext "false" @default.
- W2017643118 isRetracted "false" @default.
- W2017643118 magId "2017643118" @default.
- W2017643118 workType "article" @default.