Complexity of Deep Convolutional Neural Networks in Mobile Computing

Neural 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 exam...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Complexity (New York, N.Y.) Jg. 2020; H. 2020; S. 1 - 8
Hauptverfasser: Nazir, Shah, Khan, Habib Ullah, Jamil, Noreen, Naeem, Saad
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cairo, Egypt Hindawi Publishing Corporation 17.09.2020
Hindawi
John Wiley & Sons, Inc
Wiley
Schlagworte:
Accuracy
Algorithms
Artificial neural networks
Brain
Centroids
Counting
Electronic devices
Huffman codes
Knowledge
Learning
Mobile computing
Mobile devices
Neural networks
Neurons
Pattern recognition
Signal processing
Surveys
Time compression
Training
Video compression
Wireless networks
ISSN:1076-2787, 1099-0526
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Neural 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.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1076-2787
1099-0526
DOI:10.1155/2020/3853780