Competitive residual neural network for image classification | Zendy

Muhammad Shehzad Hanif | Zendy; Muhammad Bilal | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Competitive residual neural network for image classification

Author(s) -

Muhammad Shehzad Hanif,

Muhammad Bilal

Publication year - 2019

Publication title -

ict express

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.733

H-Index - 22

ISSN - 2405-9595

DOI - 10.1016/j.icte.2019.06.001

Subject(s) - residual , normalization (sociology) , convolutional neural network , computer science , benchmark (surveying) , artificial intelligence , margin (machine learning) , pattern recognition (psychology) , residual neural network , boosting (machine learning) , machine learning , algorithm , geodesy , sociology , anthropology , geography

We propose a novel residual network called competitive residual network (CoRN) for image classification. The proposed network is composed of residual units having two identical blocks each containing convolutional filters, batch normalization, and a maxout unit. The maxout unit enables the competition among the convolutional filters and reduces the dimensionality of the convolutional layer. The proposed network outperforms the original residual network by a significant margin and test errors on benchmark datasets (CIFAR-10/100 and SVHN) are comparable to the state-of-the-art. Using the ensemble network, we achieve a test error of 3.85% on CIFAR-10, 18.17% on CIFAR-100 and 1.59% on SVHN.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research