Please use this identifier to cite or link to this item: http://localhost:8080/xmlui/handle/123456789/1850
Full metadata record
DC FieldValueLanguage
dc.contributor.authorV, Pream Sudha-
dc.contributor.authorR, Kowsalya-
dc.date.accessioned2020-09-29T06:26:44Z-
dc.date.available2020-09-29T06:26:44Z-
dc.date.issued2015-
dc.identifier.issn2319-8354-
dc.identifier.urihttps://www.ijarse.com/images/fullpdf/1428670381_36_Research_Paper.pdf-
dc.identifier.urihttp://localhost:8080/xmlui/handle/123456789/1850-
dc.description.abstractDeep learning is an emerging research area in machine learning and pattern recognition field. Deep learning refers to machine learning techniques that use supervised or unsupervised strategies to automatically learn hierarchical representations in deep architectures for classification. The objective is to discover more abstract features in the higher levels of the representation, by using neural networks which easily separates the various explanatory factors in the data. In the recent years it has attracted much attention due to its state-of-the-art performance in diverse areas like object perception, speech recognition, computer vision, collaborative filtering and natural language processing. As the data keeps getting bigger, deep learning is coming to play a key role in providing big data predictive analytics solutions. This paper presents a brief overview of deep learning, techniques, current research efforts and the challenges involved in iten_US
dc.language.isoenen_US
dc.publisherInternational Journal of Advance Research In Science And Engineeringen_US
dc.subjectAuto-Encodersen_US
dc.subjectCNNen_US
dc.subjectDeep learningen_US
dc.subjectRBMen_US
dc.titleA SURVEY ON DEEP LEARNING TECHNIQUES APPLICATIONS AND CHALLENGESen_US
dc.typeArticleen_US
Appears in Collections:International Journals

Files in This Item:
File Description SizeFormat 
A SURVEY ON DEEP LEARNING TECHNIQUES APPLICATIONS AND CHALLENGES.docx10.33 kBMicrosoft Word XMLView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.