Prasanna Balaprakash

Latest

• Improving performance in continual learning tasks using bio-inspired architectures
• Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck
• Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck
• Improving Performance in Continual Learning Tasks using Bio-Inspired Architectures
• HPC Storage Service Autotuning Using Variational-Autoencoder-Guided Asynchronous Bayesian Optimization
• A Taxonomy of Error Sources in HPC I/O Machine Learning Models
• Application of machine learning and artificial intelligence to extend EFIT equilibrium reconstruction
• Application of machine learning and artificial intelligence to extend EFIT equilibrium reconstruction
• Unified probabilistic neural architecture and weight ensembling improves model robustness
• $łess$i$greater$In situ$łess$/i$greater$ compression artifact removal in scientific data using deep transfer learning and experience replay
• A Modular Deep Learning Pipeline for Galaxy-Scale Strong Gravitational Lens Detection and Modeling
• Neuromorphic Architectures for Edge Computing Under Extreme Environments
• Gauge: An Interactive Data-Driven Visualization Tool for HPC Application I/O Performance Analysis
• HPC I/O Throughput Bottleneck Analysis with Explainable Local Models
• In situ compression artifact removal in scientific data using deep transfer learning and experience replay
• Multilayer Neuromodulated Architectures for Memory-Constrained Online Continual Learning
• Time-series learning of latent-space dynamics for reduced-order model closure
• Towards Generalizable Models of I/O Throughput
• Adaptive Learning for Concept Drift in Application Performance Modeling
• Improving Scalability of Parallel CNN Training by Adjusting Mini-Batch Size at Run-Time
• Modular Deep Learning Analysis of Galaxy-Scale Strong Lensing Images
• Neuromorphic Architecture Optimization for Task-Specific Dynamic Learning
• Phase Segmentation in Atom-Probe Tomography Using Deep Learning-Based Edge Detection
• Using recurrent neural networks for nonlinear component computation in advection-dominated reduced-order models
• Value-Added Chemical Discovery Using Reinforcement Learning
• Modeling I/O Performance Variability Using Conditional Variational Autoencoders
• Machine Learning Based Parallel I/O Predictive Modeling: A Case Study on Lustre File Systems
• Analysis and Correlation of Application I/O Performance and System-Wide I/O Activity