TY - GEN
T1 - Investigating Existing Techniques for Designing Convolutional Neural Network Filters
AU - Karuppasamy, Arunadevi
AU - Abdessalem, Abdelhamid
AU - Hedjam, Rachid
AU - Zidoum, Hamza M.
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - In the last decades, Deep Learning (DL) has played an essential role in extracting automatically high-level features and performing complex computer vision tasks. A Convolutional Neural Network (CNN) is one of the deep learning methods that is currently attaining state-of-the-art accuracy in image classification and object recognition. CNN has three types of layers: convolutional layer, pooling layer and fully connected layer. The first two types of layers extract different levels of useful features, while the latter type is dedicated to perform classification. Traditional CNNs like AlexNet, VGGNet, GoogLeNet, ResNet use back-propagation approach in their training. Such approach requires huge amount of datasets which leads to high computational cost and suffers from vanishing gradient problem that deteriorates the quality of learning. Recently, a forward propagation approach was proposed to tackle these problems. In this paper, we summarize the results of a comparative study which we conducted on the two learning approaches.
AB - In the last decades, Deep Learning (DL) has played an essential role in extracting automatically high-level features and performing complex computer vision tasks. A Convolutional Neural Network (CNN) is one of the deep learning methods that is currently attaining state-of-the-art accuracy in image classification and object recognition. CNN has three types of layers: convolutional layer, pooling layer and fully connected layer. The first two types of layers extract different levels of useful features, while the latter type is dedicated to perform classification. Traditional CNNs like AlexNet, VGGNet, GoogLeNet, ResNet use back-propagation approach in their training. Such approach requires huge amount of datasets which leads to high computational cost and suffers from vanishing gradient problem that deteriorates the quality of learning. Recently, a forward propagation approach was proposed to tackle these problems. In this paper, we summarize the results of a comparative study which we conducted on the two learning approaches.
KW - CNN
KW - CSVM
KW - PCANet
KW - PCANet+
KW - ScatNet
KW - convolutional layer
KW - feature-maps
KW - filters
UR - http://www.scopus.com/inward/record.url?scp=85078075483&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078075483&partnerID=8YFLogxK
U2 - 10.1109/ICCCNT45670.2019.8944816
DO - 10.1109/ICCCNT45670.2019.8944816
M3 - Conference contribution
AN - SCOPUS:85078075483
T3 - 2019 10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019
BT - 2019 10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2019
Y2 - 6 July 2019 through 8 July 2019
ER -