File(s) not publicly available
A non-iterative radial basis function based quick convolutional neural network
conference contributionposted on 2021-06-24, 22:47 authored by Toshi Sinha, Brijesh 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.