File(s) not publicly available

A non-iterative radial basis function based quick convolutional neural network

conference contribution
posted on 24.06.2021, 22:47 authored by Toshi SinhaToshi Sinha, Brijesh VermaBrijesh Verma
In the past few years, Convolutional Neural Networks (CNNs) have achieved surprisingly good results for objects classification in real world images. However, training a CNN from scratch for large datasets is still a nightmare, when it comes to time and resources. The main reason for this problem is long iterative training process used in CNN's fully connected layer which is also called a classification layer. Therefore, in this paper we propose a novel approach to make the convolutional neural network quicker and more efficient for image classification tasks. The proposed approach consists of a convolutional feature extraction layer and a non-iterative radial basis function-based classification layer. The proposed approach has been evaluated on three benchmark datasets such as CIFAR-10, MNIST and Digit. The experimental results have demonstrated that the proposed approach can achieve same or higher accuracy in lesser time than the standard CNN.

Funding

Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)

History

Start Page

1

End Page

6

Number of Pages

6

Start Date

19/07/2020

Finish Date

24/07/2020

ISBN-13

9781728169262

Location

Glasgow, UK

Publisher

IEEE

Place of Publication

Piscataway, NJ

Peer Reviewed

Yes

Open Access

No

Author Research Institute

Centre for Intelligent Systems

Era Eligible

Yes

Name of Conference

International Joint Conference on Neural Networks (IJCNN 2020)

Parent Title

Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN)