Paper Info
Title
Design Of Convolution Neural Network With Frequency Selectivity For Wearable Camera Embed Glasses Based Image Recognition Systems Via Nonconvex Functional Inequality Constrained Sparse Optimization Approach
Abstract
As there is a rapid development of the wearable camera embed glasses in this decade and these wearable camera embed glasses are portable for the consumer uses, many image recognition systems are developed based on these wearable camera embed glasses. To perform the image recognition, a deep learning based convolution neural network is employed. Instead of using the conventional back propagation approach for training the weight matrices in the convolution layer of the convolution neural network, this paper proposes an optimization approach for the design of these weight matrices. In particular, the error energy between the filtered input vectors and the desirable output vectors of the convolution layer as well as the L-p norm of the weight matrices are minimized subject to the frequency selectivity specifications imposed on these weight matrices. This design problem is actually a nonconvex functional inequality constrained sparse problem. Our recently developed sparse optimization method and nonconvex functional inequality constrained optimization method are applied for finding the solution of the optimization problem.
Year
Venue
Field
2016
PROCEEDINGS 2016 IEEE 25TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE)
Computer vision,Convolution,Matrix (mathematics),Convolutional neural network,Artificial intelligence,Norm (mathematics),Deep learning,Artificial neural network,Backpropagation,Optimization problem,Mathematics
DocType
ISSN
Citations 
Conference
2163-5137
0
PageRank 
References 
Authors
0.34
0
5
Name
Order
Citations
PageRank
jing su103.72
Qing Liu242151.42
Meilin Wang3153.67
Jiangzhong Cao4245.33
Wing-Kuen Ling594.21