Don Dennis

First Year PhD Student
Electrical and Computer Engineering
Carnegie Mellon University
 dondennis [at] cmu [dot] edu
Its Me

Latest News
[Sep '19] Our work on shallow recurrent networks accepted to NeurIPS '19.
[Aug '19] Moving to CMU for my PhD.
[Jun '19] GesturePod accepted to UIST '19.
[Mar '19] Talk on fast inference on the edge at Microsoft Research Redmond. [Slides].
[Dec '18] EMI-RNN paper accepted to NeurIPS '18.
[Dec '18] GesturePod presented at NeurIPS '18 at the MLPCD workshop and covered by ZD Net.
[Nov '18] EMI-RNN implementation now part of Microsoft's EdgeML.

I am a first year PhD student in the Electrical and Computer Engineering department at CMU, advised by Prof. Virginia Smith. I am interested in general problems that arise at the intersection of Machine Learning and Systems, with a current focus on distributed optimization methods for various settings.

Prior to CMU, I spent two wonderful years as a Research Fellow at Microsoft Research India as part of the Machine Learning and Optimisation (MLO) group. There, I worked with Prateek Jain and Harsha Simhadri on algorithms for resource efficient Machine Learning.

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)

I hold a bachelors degree in Computer Science and Engineering from IIT Patna where I worked with Prof. Arijit Mondal for my thesis. 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.