We are happy to announce the 21st PyData Cambridge meetup!

Link to join the event: https://zoom.us/j/95800747674?pwd=TDhWbzArTitZbzhGYXBjR0xOZDUvdz09

IMPORTANT

Due to COVID-19 social distancing measures, this edition will be hosted online. We will send a message to all the participants, with the link to join the meeting, 24h before the event.

Agenda

19:00 - Introduction
19:15 - "Modelling with Gaussian Processes" by Vidhi Lalchand
19:45 - "What if you put your dataset in a Blender?" by Zack Akil
20:15 - End

Code of Conduct

PyData is dedicated to providing a harassment-free event experience for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of participants in any form.

The PyData Code of Conduct governs this meetup. ( http://pydata.org/code-of-conduct.html ) To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact NumFOCUS Executive Director Leah Silen (leah@numfocus.org) or organizers.

Talks

** Title: Modelling with Gaussian Processes
** Speaker: Vidhi Lalchand

Abstract:
Gaussian processes represent a powerful, non-parametric approach to probabilistic function modelling with inductive biases controlled by a kernel function. GPs are the gold standard for many real world modelling problems with moderate sized datasets, especially where the quality of predictive uncertainty is of utmost importance. In this short talk, we will first answer the question - What are Gaussian processes?, highlighting how they are different to other parametric forms of modelling functions. The second part of the talk will demonstrate how GPs are used in the regression paradigm, a workhorse of classical machine learning. This part will include a short demo in python.

Bio:
Vidhi is a PhD student at the University of Cambridge, Department of Physics. Prior to this she completed a MPhil in Scientific Computing from Cambridge (2016) and a M.Sc. in Applicable Mathematics from the London School of Economics and Political Science. Before joining Cambridge in 2015 she worked as a quantitative analyst at Credit Suisse and as a high frequency trader at the Chicago based hedge fund, Citadel Securities (Europe) between 2011 and 2015. Her supervisors are Prof. Carl Edward Rasmussen and Dr. Christopher Lester from Cambridge. Her research interests centre around approximate inference in Bayesian non-parametric models like Gaussian processes and Dirichlet processes. She is equally interested in the potential of incorporating machine learning in the science of discovery workflows in high energy physics and astronomy. She recently won the prestigious Qualcomm Innovation Fellowship (Europe) along with 4 other PhD students from Europe.

** Title: What if you put your dataset in a Blender?
** Speaker: Zack Akil

Abstract:
For making quick data viz you probably have your preferred plotting libraries' import statement committed to muscle memory, but let's say you've got some spare time on your hands to craft whatever visualisation your mind can conjure? enter Blender (https://www.blender.org/). An open source 3D animation tool that also has an elegant python interface, I'll show you how you can even make the Iris dataset interesting to look at again.

Zack Akil (@ZackAkil) is a machine learning engineer & developer advocate at Google who spends most of his time building experimental ML applications that help inspire other developers to utilise ML in new ways.