Asad Khan

| Deep Learning |
| High Performance Computing |
| Multimessenger Astrophysics |

Projects:

Card image cap
DES Galaxy Classification

Transfer Learning through Convolutional Neural Networks to do unsupervised clustering of Galaxies in the DR1 dataset.

Card image cap
Scaling Deep Learning

Parallelizing the training of Deep Neural Networks on multiple GPUs

Card image cap
Gravitational Waves Parameter Estimation

Physics-inspired deep learning to characterize the signal manifold of quasi-circular, spinning, non-precessing binary black hole mergers

Card image cap
Deep Learning for Gravitational Wave Detection

Deep learning ensemble for real-time gravitational wave detection of spinning binary black hole mergers

Card image cap
Interpreting Natural Language Processing

Probing Interpretability of Deep Learning models for Natural Language Processing, using BERT for Named Entity Recognition as a case study.

Publications:

  1. Interpretable AI forecasting for numerical relativity waveforms of quasi-circular, spinning, non-precessing binary black hole mergers
    Physical Review D, arXiv:2110.06968
  2. Physics-inspired deep learning to characterize the signal manifold of quasi-circular, spinning, non-precessing binary black hole mergers
    Physics Letters B, arXiv:2004.09524
  3. Deep learning at scale for the construction of galaxy catalogs in the Dark Energy Survey
    Physics Letters B, arXiv:1812.02183
  4. Accelerated, scalable and reproducible AI-driven gravitational wave detection
    Nature Astronomy, arXiv:2012.08545
  5. Deep learning ensemble for real-time gravitational wave detection of spinning binary black hole mergers
    Physics Letters B, arXiv:2010.15845v1
  6. Enabling real-time multi-messenger astrophysics discoveries with deep learning
    Nature Reviews Physics, arXiv:1911.11779
  7. Convergence of Artificial Intelligence and High Performance Computing on NSF-supported Cyberinfrastructure
    Journal of Big Data, arXiv:1902.00522
  8. Inference-optimized AI and high performance computing for gravitational wave detection at scale
    Frontiers in Artificial Intelligence, arXiv:2201.11133
  9. AI and extreme scale computing to learn and infer the physics of higher order gravitational wave modes of quasi-circular, spinning, non-precessing binary black hole mergers
    arXiv:2112.07669
  10. Interpreting a Machine Learning Model for Detecting Gravitational Waves
    arXiv:2202.07399
  11. 280 GHz Focal Plane Unit Design and Characterization for the SPIDER-2 Suborbital Polarimeter
    arXiv:1711.04169v2

Reviews:

  1. PyFstat: a Python package for continuous gravitational-wave data analysis, D. Keitel, et al.
    The Journal of Open Source Software

Conferences and Talks:

  • 237th Meeting of the American Astronomical Society. Virtual [January, 2021]
  • 30th Annual Midwest Relativity Meeting, University of Notre Dame, IN [October, 2020]
  • 2020 Accelerated Artificial Intelligence for Big-Data Experiments Conference, NCSA, Champaign, IL [October, 2020]
  • American Physical Society (APS) April Meeting, Wachington D.C. [April, 2020]
  • 235th Meeting of the American Astronomical Society, Honolulu, Hawai'i [January, 2020]
  • URSSI Winter School in Research Software Engineering, University of Washington Seattle [December, 2019]
  • Current and Future Development of Neutron Scattering Techniques for Time-Resolved Studies, Oak Ridge National Laboratory [October, 2019]
  • AstroInformatics, Caltech [June, 2019]
  • Deep Learning for Multimessenger Astrophysics: Real-time Discovery at Scale, NCSA [October, 2018]
  • Data Visualization And Exploration in the LSST Era, NCSA [June, 2018]
  • CMB Detectors And Instrumentation, University of Chicago [August, 2017]