A
Amit Ganatra
Researcher at Charotar University of Science and Technology
Publications - 88
Citations - 1397
Amit Ganatra is an academic researcher from Charotar University of Science and Technology. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 16, co-authored 79 publications receiving 1066 citations.
Papers
More filters
Journal ArticleDOI
Behaviour Analysis of Multilayer Perceptrons with Multiple Hidden Neurons and Hidden Layers
TL;DR: Behavioral analysis of different number of hidden layers and differentNumber of hidden neurons is discussed, it's very difficult to select number ofhidden layers and hidden neurons.
A Comparative Study of Training Algorithms for Supervised Machine Learning
Hetal Bhavsar,Amit Ganatra +1 more
TL;DR: This research is related to the study of the existing classification algorithm and their comparative in terms of speed, accuracy, scalability and other issues which in turn would help other researchers in studying the existing algorithms as well as developing innovative algorithms for applications or requirements which are not available.
Journal ArticleDOI
Characterization of poly-4-hydroxybutyrate mesh for hernia repair applications.
David P. Martin,Amit Badhwar,Devang V. Shah,Said Rizk,Stephen N. Eldridge,Darcy H. Gagne,Amit Ganatra,Roger E. Darois,Simon F. Williams,Hsin-Chien Tai,Jeffrey R. Scott,Jeffrey R. Scott +11 more
TL;DR: In vitro and in vivo data suggest that Phasix mesh provides a durable scaffold for mechanical reinforcement of soft tissue reconstruction and successfully returning the mechanical properties of repaired host tissue to its native state over an extended time period.
Journal ArticleDOI
Determination of over-learning and over-fitting problem in back propagation neural network
TL;DR: Methods for choosing training set which is used to prevent over-learning are proposed and the concept of a reproducing is proposed.
Proceedings ArticleDOI
A Deep Learning Approach for Face Detection using YOLO
TL;DR: This paper compares the accuracy of detecting the face in an efficient manner with respect to the traditional approach and uses the convolutional neural network as an approach of deep learning for detecting faces from videos.