Inception-VR70: An Advanced Inception-Net Artificial Intelligence based Novel Hybrid Architecture

Abstract

In the present day, Convolutional Neural Network (CNN) architectures are undergoing a great deal of development, which has resulted in the creation of models like VGG16, ResNet50, InceptionV3 etc., that significantly increase accuracy. Yet, a network that can deal with overfitting, a significant challenge in deep learning besides having greater accuracy and extracting useful features is required. In this paper, we propose a Deep hybrid model which is an inception of pretrained models with a different input image size, significantly leading to improved accuracy which has been tested on various datasets of different domains including health care, agriculture, and the remote sensing. The performance of this hybrid model is superior to the standalone pretrained models. It is observed that the hybrid model proposed in this paper merely has overfitting despite of having very deep layers compared to all other deep architectures. Best accuracy achieved for this model is 99.64% being train accuracy and 96.33% being test accuracy for the Satellite Images of Hurricane Damage dataset with minimum overfitting.