)
{first name}souza{last name} at gmail dot com
I'm a Researcher at 3778 Healthcare working with Machine Learning for Healthcare. Previously, I was Head of Data Science at Linx Impulse and a Researcher at the CERTI Foundation where I worked with Signal Processing and Embedded Systems.
I'm interested in learning more about the intersection between Statistical Learning and Deep Learning as well as how Machine Learning can be seen as an Information Theory problem. I'm also interested in their applications to Health and Privacy.
Originally, I am from Florianópolis, Brazil but I've lived in New Jersey, Orlando, Toronto and São Paulo as well as other smaller cities in the south of Brazil. I enjoy reading, playing american football and KSP
I'm interested in learning more about the intersection between Statistical Learning and Deep Learning as well as how Machine Learning can be seen as an Information Theory problem. I'm also interested in their applications to Health and Privacy.
Originally, I am from Florianópolis, Brazil but I've lived in New Jersey, Orlando, Toronto and São Paulo as well as other smaller cities in the south of Brazil. I enjoy reading, playing american football and KSP
Interests
- Statistical Learning
- Information Theory
- Generative Models
- Privacy in Machine Learning
- Machine Learning for Healthcare
Education
-
Exchange Program, 2013
University of Toronto
-
BSc in Electronics Engineering, 2015
Federal University of Santa Catarina
News
- 03/Dec/2019 - Proof of Novelty was awarded by Blockchain@UBC!
- 15/Nov/2019 - Finished writing Proof of Novelty.
- 21/Oct/2019 - Preprint of Ward2ICU posted on arXiv.
- 02/Oct/2019 - This page was created!
- 19/Sep/2019 - Claimed a paper for the Reproducibility Challenge @ NeurIPS 2019
Papers
- Severo, D., et al. “Ward2ICU: A Vital Signs Dataset of Inpatients from the General Ward.” arXiv preprint arXiv:1910.00752 (2019).
- Severo, D. “Proof of Novelty”. figshare preprint 10324883
Open Source Contributions
- dask/Dask: Parallel computing with task scheduling
- dask/Dask-ML: Scalable Machine Learn with Dask
- 3778/Ward2ICU: Source code for arXiv preprint arXiv:1910.00752 (2019).
- 3778/ml-challenge: 3778’s Machine Learning Challenge.
Other work
- Mathematical proof of functionality, of a highly efficient pseudo-random number generator: The Ziggurat Method
- How can we keep the simplicity and power of pandas, while extending it to be out-of-core and parallel? Ad hoc Big Data Analysis with Dask
- An Introduction to Handling Time-series in Pandas and numpy