Search Results - "Balaprakash, Prasanna"

Time-series learning of latent-space dynamics for reduced-order model closure by Maulik, Romit, Mohan, Arvind, Lusch, Bethany, Madireddy, Sandeep, Balaprakash, Prasanna, Livescu, Daniel

“…We study the performance of long short-term memory networks (LSTMs) and neural ordinary differential equations (NODEs) in learning latent-space representations…”
Get full text

Autotuning in High-Performance Computing Applications by Balaprakash, Prasanna, Dongarra, Jack, Gamblin, Todd, Hall, Mary, Hollingsworth, Jeffrey K., Norris, Boyana, Vuduc, Richard

“…Autotuning refers to the automatic generation of a search space of possible implementations of a computation that are evaluated through models and/or empirical…”
Get full text

CANDLE/Supervisor: a workflow framework for machine learning applied to cancer research by Wozniak, Justin M, Jain, Rajeev, Balaprakash, Prasanna, Ozik, Jonathan, Collier, Nicholson T, Bauer, John, Xia, Fangfang, Brettin, Thomas, Stevens, Rick, Mohd-Yusof, Jamaludin, Cardona, Cristina Garcia, Essen, Brian Van, Baughman, Matthew

“…Current multi-petaflop supercomputers are powerful systems, but present challenges when faced with problems requiring large machine learning workflows. Complex…”
Get full text

Graph neural networks for detecting anomalies in scientific workflows by Jin, Hongwei, Raghavan, Krishnan, Papadimitriou, George, Wang, Cong, Mandal, Anirban, Kiran, Mariam, Deelman, Ewa, Balaprakash, Prasanna

“…Identifying and addressing anomalies in complex, distributed systems can be challenging for reliable execution of scientific workflows. We model these…”
Get full text

Phase Segmentation in Atom-Probe Tomography Using Deep Learning-Based Edge Detection by Madireddy, Sandeep, Chung, Ding-Wen, Loeffler, Troy, Sankaranarayanan, Subramanian K. R. S., Seidman, David N., Balaprakash, Prasanna, Heinonen, Olle

“…Atom-probe tomography (APT) facilitates nano- and atomic-scale characterization and analysis of microstructural features. Specifically, APT is well suited to…”
Get full text

Streamlining Ocean Dynamics Modeling with Fourier Neural Operators: A Multiobjective Hyperparameter and Architecture Optimization Approach by Sun, Yixuan, Sowunmi, Ololade, Egele, Romain, Narayanan, Sri Hari Krishna, Van Roekel, Luke, Balaprakash, Prasanna

“…Training an effective deep learning model to learn ocean processes involves careful choices of various hyperparameters. We leverage DeepHyper’s advanced search…”
Get full text

AutoPhaseNN: unsupervised physics-aware deep learning of 3D nanoscale Bragg coherent diffraction imaging by Yao, Yudong, Chan, Henry, Sankaranarayanan, Subramanian, Balaprakash, Prasanna, Harder, Ross J., Cherukara, Mathew J.

“…The problem of phase retrieval underlies various imaging methods from astronomy to nanoscale imaging. Traditional phase retrieval methods are iterative and are…”
Get full text

Multi-fidelity reinforcement learning with control variates by Khairy, Sami, Balaprakash, Prasanna

“…In many computational science and engineering applications, the output of a system of interest corresponding to a given input can be queried at different…”
Get full text

Estimation-based ant colony optimization and local search for the probabilistic traveling salesman problem by Balaprakash, Prasanna, Birattari, Mauro, Stützle, Thomas, Yuan, Zhi, Dorigo, Marco

“…The use of ant colony optimization for solving stochastic optimization problems has received a significant amount of attention in recent years. In this paper,…”
Get full text

Uncertainty Quantification for Traffic Forecasting Using Deep-Ensemble-Based Spatiotemporal Graph Neural Networks by Mallick, Tanwi, Macfarlane, Jane, Balaprakash, Prasanna

“…Deep-learning-based data-driven forecasting methods have achieved impressive results for traffic forecasting. Specifically, spatiotemporal graph neural…”
Get full text

Constrained Deep Reinforcement Learning for Energy Sustainable Multi-UAV Based Random Access IoT Networks With NOMA by Khairy, Sami, Balaprakash, Prasanna, Cai, Lin X., Cheng, Yu

“…In this paper, we apply the Non-Orthogonal Multiple Access (NOMA) technique to improve the massive channel access of a wireless IoT network where solar-powered…”
Get full text

Graph-Partitioning-Based Diffusion Convolutional Recurrent Neural Network for Large-Scale Traffic Forecasting by Mallick, Tanwi, Balaprakash, Prasanna, Rask, Eric, Macfarlane, Jane

“…Traffic forecasting approaches are critical to developing adaptive strategies for mobility. Traffic patterns have complex spatial and temporal dependencies…”
Get full text

Stabilized neural ordinary differential equations for long-time forecasting of dynamical systems by Linot, Alec J., Burby, Joshua W., Tang, Qi, Balaprakash, Prasanna, Graham, Michael D., Maulik, Romit

“…In data-driven modeling of spatiotemporal phenomena careful consideration is needed in capturing the dynamics of the high wavenumbers. This problem becomes…”
Get full text

Modeling design and control problems involving neural network surrogates by Yang, Dominic, Balaprakash, Prasanna, Leyffer, Sven

“…We consider nonlinear optimization problems that involve surrogate models represented by neural networks. We demonstrate first how to directly embed neural…”
Get full text

Multi-fidelity reinforcement learning framework for shape optimization by Bhola, Sahil, Pawar, Suraj, Balaprakash, Prasanna, Maulik, Romit

“…Deep reinforcement learning (DRL) is a promising outer-loop intelligence paradigm which can deploy problem solving strategies for complex tasks. Consequently,…”
Get full text

Machine-learning-aided density functional theory calculations of stacking fault energies in steel by Samanta, Amit, Balaprakash, Prasanna, Aubry, Sylvie, Lin, Brian K.

Get full text

Continual Learning via Dynamic Programming by Krishnan, R., Balaprakash, Prasanna

“…Continual learning (CL) algorithms seek to train a model when faced with similar tasks observed in a sequential manner. Despite promising methodological…”
Get full text

The unreasonable effectiveness of early discarding after one epoch in neural network hyperparameter optimization by Egele, Romain, Mohr, Felix, Viering, Tom, Balaprakash, Prasanna

“…To reach high performance with deep learning, hyperparameter optimization (HPO) is essential. This process is usually time-consuming due to costly evaluations…”
Get full text

Machine-learning-aided density functional theory calculations of stacking fault energies in steel by Samanta, Amit, Balaprakash, Prasanna, Aubry, Sylvie, Lin, Brian K.

“…A combined large-scale first principles approach with machine learning and materials informatics is proposed to quickly sweep the chemistry-composition space…”
Get full text

A Gradient-Aware Search Algorithm for Constrained Markov Decision Processes by Khairy, Sami, Balaprakash, Prasanna, Cai, Lin X.

“…The canonical solution methodology for finite constrained Markov decision processes (CMDPs), where the objective is to maximize the expected infinite-horizon…”
Get full text