P
Pravin Chandra
Researcher at Guru Gobind Singh Indraprastha University
Publications - 111
Citations - 1267
Pravin Chandra is an academic researcher from Guru Gobind Singh Indraprastha University. The author has contributed to research in topics: Artificial neural network & Initialization. The author has an hindex of 16, co-authored 111 publications receiving 1045 citations. Previous affiliations of Pravin Chandra include University of Delhi.
Papers
More filters
Journal ArticleDOI
An activation function adapting training algorithm for sigmoidal feedforward networks
Pravin Chandra,Yogesh Singh +1 more
TL;DR: A new activation function adapting algorithm is proposed for sigmoidal feedforward neural network training and it is demonstrated that the proposed algorithm can be an order of magnitude faster than the backpropagation algorithm.
Journal ArticleDOI
Bayesian Regularization in a Neural Network Model to Estimate Lines of Code Using Function Points
TL;DR: Results demonstrate that the neural network models trained using Bayesian Regularization provide the best results and are suitable for estimating the Source Lines of Code.
Journal ArticleDOI
Measurement of Software Maintainability Using a Fuzzy Model
TL;DR: This study proposes a four parameter integrated measure of software maintainability using a fuzzy model and includes empirical data of maintenance time of projects which has been used to validate the proposed model.
Journal ArticleDOI
Feedforward sigmoidal networks - equicontinuity and fault-tolerance properties
Pravin Chandra,Yogesh Singh +1 more
TL;DR: The universal approximation results are summarized to identify the function sets represented by the sigmoidal FFANNs with the universal approximation properties and the equicontinuous properties of the identified sets is analyzed.
Constructive neural networks: a review
TL;DR: This paper reviews constructive neural network algorithms that constructing feedforward architecture for regression problems and recently proposed two constructive algorithms that emphasize on architectural adaptation and functional adaptation during training.