Show simple item record

AuthorNaeem, Saad
AuthorJamil, Noreen
AuthorKhan, Habib Ullah
AuthorNazir, Shah
Available date2022-12-28T11:39:00Z
Publication Date2020-09-17
Publication NameComplexity
Identifierhttp://dx.doi.org/10.1155/2020/3853780
CitationNaeem, S., Jamil, N., Khan, H. U., & Nazir, S. (2020). Complexity of deep convolutional neural networks in mobile computing. Complexity, 2020.
ISSN1076-2787
URIhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85092181597&origin=inward
URIhttp://hdl.handle.net/10576/37761
AbstractNeural networks employ massive interconnection of simple computing units called neurons to compute the problems that are highly nonlinear and could not be hard coded into a program. These neural networks are computation-intensive, and training them requires a lot of training data. Each training example requires heavy computations. We look at different ways in which we can reduce the heavy computation requirement and possibly make them work on mobile devices. In this paper, we survey various techniques that can be matched and combined in order to improve the training time of neural networks. Additionally, we also review some extra recommendations to make the process work for mobile devices as well. We finally survey deep compression technique that tries to solve the problem by network pruning, quantization, and encoding the network weights. Deep compression reduces the time required for training the network by first pruning the irrelevant connections, i.e., the pruning stage, which is then followed by quantizing the network weights via choosing centroids for each layer. Finally, at the third stage, it employs Huffman encoding algorithm to deal with the storage issue of the remaining weights.
SponsorQatar University [IRCC-2020-009].
Languageen
PublisherHindawi
SubjectConvolutional neural networks
Training example
Signal encoding
TitleComplexity of Deep Convolutional Neural Networks in Mobile Computing
TypeArticle
Volume Number2020
ESSN1099-0526
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record