Autistic Disorder Spectrum Using Inception V3

Abstract

When diagnosed early, autism spectrum disorder (ASD) can cut healthcare expenses by as much as 80% if not more. On the ImageNet dataset, Inception v3 has been demonstrated to achieve above 75% accuracy in picture recognition. One of the techniques used in the healthcare industry is called Deep Transfer Learning (DTL). Inception V3 gives 86% accuracy for Image dataset of Autistic Kids, train loss 0.6695, Val loss 0.9823 .The model made up many convolution layers with wide range of parameters, pooling layers helps in reducing the dimensions which helps in nding feature maps efciently. Batch Normalization, spatial factorization, using Auxiliary lters and reduce Grid size are the major highlights.