Don Dennis

Research Fellow
Machine Learning and Optimization Group
Microsoft Research India
 t-dodenn [at] microsoft [dot] com
 donkdennis [at] gmail [dot] com
Its Me

Latest News
[Mar '19]   Talk on EMI-RNN at Microsoft Research Redmond. [Slides soon]
[Jan '19]   Manuscript on shallow recurrent networks submitted to ICML '19.
[Dec '18]   Manuscript describing EMI-RNN algorithm accepted to NeurIPS '18.
[Dec '18]   GesturePod presented at NeurIPS '18 at the MLPCD workshop.
[Dec '18]   GesturePod submitted to CHI'19 and covered by ZD Net.
[Nov '18]   EMI-RNN implementation now part of Microsoft's EdgeML.

I am a Research Fellow at Microsoft Research India, where I work with Prateek Jain and Harsha Simhadri in the Machine Learning and Optimisation (MLO) group and Intelligent Devices Expedition group. I do research on theoretically sound and practical ML algorithms that can bring state-of-the-art machine learning to severely resource-constrained devices. As concrete examples,

  • My EMI-RNN algorithm (NeurIPS '18) brought accurate real-time key-word spotting capabilities to devices like Raspberry Pi0 and MXChip.
  • My ProtoNN powered ML pipeline on GesturePod does robust and real-time gesture recognition on a tiny grain sized processor. GesturePod has been widely covered by the media and was Microsoft's official demonstration at NeurIPS '18.

Research Interests
    · Machine Learning (ML) - Theoretical and Applied Aspects
    · Robust and Reliable ML for Systems and Devices
    · Resource Efficient ML
    · ML Embedded in Devices (Robotics/IoT/Autonomous Systems)

Prior to joining Microsoft Research, I did my undergraduate at IIT Patna, with my thesis work supervised by Dr. Arijit Mondal. My current focus is primarily academic, but I strongly feel about the impact cutting-edge technology can have for social good. During our undergraduate years, Rito, Karan, Prashant and I failed at scaling up Weave; a venture focused on creating micro-entrepreneurs in a marginalized weaver community.

The Weave journey somewhere along the line transformed into a new venture, rooting for healthcare access and affordability, using deep learning for diagnostics at ChironX. I continue to actively collaborate with Rito and Prashant at ChironX on designing their deep learning solutions and architectures.