H
Hariprasad Kodamana
Researcher at Indian Institute of Technology Delhi
Publications - 51
Citations - 707
Hariprasad Kodamana is an academic researcher from Indian Institute of Technology Delhi. The author has contributed to research in topics: Computer science & Expectation–maximization algorithm. The author has an hindex of 11, co-authored 35 publications receiving 338 citations. Previous affiliations of Hariprasad Kodamana include University of Alberta & Indian Institutes of Technology.
Papers
More filters
Journal ArticleDOI
Predicting Young's modulus of oxide glasses with sparse datasets using machine learning
Suresh Bishnoi,Sourabh Singh,R. Ravinder,Mathieu Bauchy,Nitya Nand Gosvami,Hariprasad Kodamana,N. M. Anoop Krishnan +6 more
TL;DR: In this paper, Gaussian Process Regression (GPR) was used to predict Young's modulus for silicate glasses having a sparse dataset and showed that GPR significantly outperforms NN for the sparse dataset while ensuring no overfitting.
Journal ArticleDOI
Process monitoring using a generalized probabilistic linear latent variable model
TL;DR: The paper presents insightful equivalence between the classical multivariate techniques for process monitoring and their probabilistic counterparts, which is obtained by restricting the generalized model.
Journal ArticleDOI
Deep learning aided rational design of oxide glasses
R. Ravinder,Karthikeya H. Sridhara,Suresh Bishnoi,Hargun Singh Grover,Mathieu Bauchy,Jayadeva,Hariprasad Kodamana,N. M. Anoop Krishnan +7 more
TL;DR: In this article, a large dataset of glasses comprising of up to 37 oxide components and more than 100,000 glass compositions was used to develop a series of new design charts, termed as glass selection charts, which enable the rational design of functional glasses for targeted applications by identifying unique compositions that satisfy two or more constraints, on both compositions and properties.
Journal ArticleDOI
Approaches to robust process identification: A review and tutorial of probabilistic methods
TL;DR: A general introduction to the probabilistic methods for robust identification is provided, the main steps involved in the development of models are illustrated, and the related literature is reviewed.
Journal ArticleDOI
Gaussian process modelling with Gaussian mixture likelihood
TL;DR: This work proposes to employ a mixture of two Gaussian distributions as the noise model to capture both regular noise and irregular noise, thereby enhancing the robustness of the regression model.