Saaketh Desai
Purdue University
34 Papers
11 Citations
Saaketh Desai is an academic researcher from Purdue University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 5, co-authored 18 publications. Previous affiliations of Saaketh Desai include Indian Institute of Technology Roorkee.
Chat about Author
Papers
Neural network reactive force field for C, H, N, and O systems
Pilsun Yoo,Michael Sakano,Saaketh Desai,Mahbubul Islam,Mahbubul Islam,Peilin Liao,Alejandro Strachan +6 more
- 22 Jan 2021
TL;DR: The authors developed a neural network reactive force field (NNRF) for CHNO systems to describe the decomposition and reaction of the high-energy nitramine 1,3,5-trinitroperhydro-1,3-5-triazine (RDX).
An investigation of the interactions between an E. coli bacterial quorum sensing biosensor and chitosan-based nanocapsules
TL;DR: The "stoichiometric" ratio of NC and bacteria has a strong influence on the bacterial behavior and influences the quorum sensing response, particularly due to the aggregation driven by NC.
Parsimonious neural networks learn interpretable physical laws.
Saaketh Desai,Alejandro Strachan +1 more
TL;DR: This article proposed parsimonious neural networks (PNNs) that combine neural networks with evolutionary optimization to find models that balance accuracy with parsimony, which can be used to discover interpretable physical laws from data.
•Posted Content
Parsimonious neural networks learn interpretable physical laws
Saaketh Desai,Alejandro Strachan +1 more
TL;DR: P parsimonious neural networks (PNNs) that combine neural networks with evolutionary optimization to find models that balance accuracy with parsimony are proposed and demonstrated by developing models for classical mechanics and to predict the melting temperature of materials from fundamental properties.
19
•Posted Content
Implementing a neural network interatomic model with performance portability for emerging exascale architectures
TL;DR: This work re-implement a neural network interatomic model in CabanaMD, an MD proxy application, built on libraries developed for performance portability, and shows significantly improved on-node scaling in this complex kernel as compared to a current LAMMPS implementation.
15