42 citations · 207 across the 23 of their papers we have counts for
24 papers
Closed-Form Optimal Weight Splitting for Matrix-Vector Multiply on Noisy In-Memory Accelerators
Mehmet Aktukmak, David A. Roberts
Analog in-memory computing performs the matrix-vector multiplications of neural networks directly inside the memory array, which saves time and energy. But each memory cell stores…
HyDeMiC: A Deep Learning-based Mineral Classifier using Hyperspectral Data
M. L. Mamud, Piyoosh Jaysaval, Frederick D Day-Lewis +1
Hyperspectral imaging (HSI) has emerged as a powerful remote sensing tool for mineral exploration, capitalizing on unique spectral signatures of minerals. However, traditional clas…
Reactive Transport Modeling with Physics-Informed Machine Learning for Critical Minerals Applications
K. Adhikari, Md. Lal Mamud, M. K. Mudunuru +1
This study presents a physics-informed neural network (PINN) framework for reactive transport modeling for simulating fast bimolecular reactions in porous media. Accurate character…
Quantifying local and global mass balance errors in physics-informed neural networks
Md Lal Mamud, Maruti K. Mudunuru, Satish Karra +1
Physics-informed neural networks (PINN) have recently become attractive for solving partial differential equations (PDEs) that describe physics laws. By including PDE-based loss fu…
Perspectives on AI Architectures and Co-design for Earth System Predictability
Maruti K. Mudunuru, James A. Ang, Mahantesh Halappanavar +8
Recently, the U.S. Department of Energy (DOE), Office of Science, Biological and Environmental Research (BER), and Advanced Scientific Computing Research (ASCR) programs organized…
CoolPINNs: A Physics-informed Neural Network Modeling of Active Cooling in Vascular Systems
N. V. Jagtap, M. K. Mudunuru, K. B. Nakshatrala
Emerging technologies like hypersonic aircraft, space exploration vehicles, and batteries avail fluid circulation in embedded microvasculatures for efficient thermal regulation. Mo…