29 citations · 70 across the 18 of their papers we have counts for
6 papers · 1 filter
Large Deviations for Accelerating Neural Networks Training
Sreelekha Guggilam, Varun Chandola, Abani Patra
Artificial neural networks (ANNs) require tremendous amount of data to train on. However, in classification models, most data features are often similar which can lead to increase…
An Ensemble-Based Deep Framework for Estimating Thermo-Chemical State Variables from Flamelet Generated Manifolds
Amol Salunkhe, Georgios Georgalis, Abani Patra +1
Complete computation of turbulent combustion flow involves two separate steps: mapping reaction kinetics to low-dimensional manifolds and looking-up this approximate manifold durin…
Combined Data and Deep Learning Model Uncertainties: An Application to the Measurement of Solid Fuel Regression Rate
Georgios Georgalis, Kolos Retfalvi, Paul E. DesJardin +1
In complex physical process characterization, such as the measurement of the regression rate for solid hybrid rocket fuels, where both the observation data and the model used have…
Anomaly Detection for High-Dimensional Data Using Large Deviations Principle
Sreelekha Guggilam, Varun Chandola, Abani Patra
Most current anomaly detection methods suffer from the curse of dimensionality when dealing with high-dimensional data. We propose an anomaly detection algorithm that can scale to…
A Forward Backward Greedy approach for Sparse Multiscale Learning
Prashant Shekhar, Abani Patra
Multiscale Models are known to be successful in uncovering and analyzing the structures in data at different resolutions. In the current work we propose a feature driven Reproducin…
Hierarchical regularization networks for sparsification based learning on noisy datasets
Prashant Shekhar, Abani Patra
We propose a hierarchical learning strategy aimed at generating sparse representations and associated models for large noisy datasets. The hierarchy follows from approximation spac…