Pitfalls of applying Machine Learning to Scientific Software

Date and Time: 
Tuesday April 9th 2019
CG Auditorium
Davide Del Vento

In the last decade, Machine Learning has experienced a dramatic increase of performance. This has corresponded to an understandable hype especially for the remarkable results achieved in some cases.

Practitioners of Scientific Disciplines have become interested in utilizing new Machine Learning techniques, and have sometimes started doing so with mixed success.

In this talk I will briefly describe some of the common Traps, Pitfalls and Misconceptions of Machine Learning as relevant to the Scientific Discipline, and especially how to avoid them.

Speaker Description: 
Davide Del Vento is Software Engineer at National Center for Atmospheric Research, where he has worked since 2008 as a High Performance Computing Specialist. In this role, he provides assistance to the UCAR computing community of scientists and programmers on a variety of topics, including optimization and tuning, parallel computing, data analysis and debugging. He contributes to design, development, testing and maintenance of local software packages. Davide also serves as a Software Engineer for the XSEDE Novel and Innovative Projects (NIP) group and for the XSEDE Extended Collaborative Support Services (ECSS) program. In 2018 he was chosen to be XSEDE Campus Champion for NCAR.Moreover, Davide is the Chairman of the Software Engineering Assembly since 2010.Earlier in his career he worked as a member of the control team for the Visible InfraRed Thermal Imaging Spectrometer onboard the Venus Express mission from the European Space Agency. The mission was proposed in 2001, launched in 2005 and operational around the planet Venus from 2006 to 2014.Davide has a MS in Physics from University of Rome Tor Vergata and a Ph.D. in Physics from University of Rome Tre respectively.
PDF icon MLPitfalls_SEA2019.pdf2.28 MB

Event Category: