[HTML][HTML] Gradient boosting Bayesian neural networks via Langevin MCMC

G Bai, R Chandra - Neurocomputing, 2023 - Elsevier
Bayesian neural networks harness the power of Bayesian inference which provides an
approach to neural learning that not only focuses on accuracy but also uncertainty …

Distributed Bayesian optimisation framework for deep neuroevolution

R Chandra, A Tiwari - Neurocomputing, 2022 - Elsevier
Neuroevolution is a machine learning method for evolving neural networks parameters and
topology with a high degree of flexibility that makes them applicable to a wide range of …

Bayesian graph convolutional neural networks via tempered MCMC

R Chandra, A Bhagat, M Maharana, PN Krivitsky - IEEE Access, 2021 - ieeexplore.ieee.org
Deep learning models, such as convolutional neural networks, have long been applied to
image and multi-media tasks, particularly those with structured data. More recently, there …

Revisiting Bayesian autoencoders with MCMC

R Chandra, M Jain, M Maharana, PN Krivitsky - IEEE Access, 2022 - ieeexplore.ieee.org
Autoencoders gained popularity in the deep learning revolution given their ability to
compress data and provide dimensionality reduction. Although prominent deep learning …

Surrogate-assisted Bayesian inversion for landscape and basin evolution models

R Chandra, D Azam, A Kapoor… - Geoscientific Model …, 2020 - gmd.copernicus.org
The complex and computationally expensive nature of landscape evolution models poses
significant challenges to the inference and optimization of unknown model parameters …

[HTML][HTML] Memory capacity of recurrent neural networks with matrix representation

A Renanse, A Sharma, R Chandra - Neurocomputing, 2023 - Elsevier
It is well known that canonical recurrent neural networks (RNNs) face limitations in learning
long-term dependencies, which have been addressed by memory structures in long short …

[PDF][PDF] Revisiting Bayesian Autoencoders With MCMC

M MAHARANA, PN KRIVITSKY - researchgate.net
Autoencoders gained popularity in the deep learning revolution given their ability to
compress data and provide dimensionality reduction. Although prominent deep learning …