Role of Structural and Conformational Diversity for Machine Learning Potentials

no code implementations • 30 Oct 2023 • Nikhil Shenoy, Prudencio Tossou, Emmanuel Noutahi, Hadrien Mary, Dominique Beaini, Jiarui Ding

In the field of Machine Learning Interatomic Potentials (MLIPs), understanding the intricate relationship between data biases, specifically conformational and structural diversity, and model generalization is critical in improving the quality of Quantum Mechanics (QM) data generation efforts.

A Case for Rejection in Low Resource ML Deployment

1 code implementation • 12 Aug 2022 • Jerome White, Pulkit Madaan, Nikhil Shenoy, Apoorv Agnihotri, Makkunda Sharma, Jigar Doshi

Building reliable AI decision support systems requires a robust set of data on which to train models; both with respect to quantity and diversity.

Position

Impact of data-splits on generalization: Identifying COVID-19 from cough and context

1 code implementation • 5 Jun 2021 • Makkunda Sharma, Nikhil Shenoy, Jigar Doshi, Piyush Bagad, Aman Dalmia, Parag Bhamare, Amrita Mahale, Saurabh Rane, Neeraj Agrawal, Rahul Panicker

Using cough and context (symptoms and meta-data) represent such a promising approach.