Primary Interests

Microarchitecture

Reconfigurable Computing

Operating Systems

Machine Simulation / Emulation

High-performance and Cloud Computing

Publications

Optimizing isotope substitution in graphene for thermal conductivity minimization by genetic algorithm driven molecular simulations. Michael Davies, Baskar Ganapathysubramanian, Ganesh Balasubramanian. 2017, Applied Physics Letters.

Automated design for microfluid flow sculpting: multi-resolution approaches, efficient encoding, and GPU implementation. Daniel Stoecklein, Michael Davies, Nadab Wubshet, Jonathan Le, Baskar Ganapathysubramanian. 2017, Journal of Fluids Engineering.

Deep Learning for Flow Sculpting: Insights into Efficient Learning using Scientific Simulation Data. Daniel Stoecklein, Kin Gwn Lore, Michael Davies, Soumik Sarkar, Baskar Ganapathysubramanian. 2017, Scientific Reports.

Deep Action Sequence Learning for Causal Shape Transformation. Kin Gwn Lore, Daniel Stoecklein, Michael Davies, Baskar Ganapathysubramanian, Soumik Sarkar. 2016, arXiv preprint.

Hierarchical feature extraction for efficient design of microfluidic flow patterns. Kin Gwn Lore, Daniel Stoecklein, Michael Davies, Baskar Ganapathysubramanian, Soumik Sarkar. 2015, Proceedings of The 1st International Workshop on “Feature Extraction: Modern Questions and Challenges”, NIPS.