We are happy to announce the 17th PyData Cambridge meetup!

Many thanks to Raspberry Pi, who host the group.

Agenda

18:45 - Doors open
19:00 - Introduction
19:10 - "Building a Wide & Deep Learning Model with PyTorch" (talk) by Javier Rodriguez Zaurin
19:55 - Interval / snacks provided
20:15 - " Introducing the AI lab at the British Antarctic Survey" by Anita Faul, British Antarctic Survey
21:00 - End (Pub TBA)

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

** Building a Wide & Deep Learning Model with PyTorch
** By Javier Rodriguez Zaurin

Wide & Deep Learning was popularised by Heng-Tze Cheng et al., 2016 in their paper "Wide & Deep Learning for Recommender Systems". Since then, it has become ubiquitous in a number of applications beyond recommendations algorithms due to its flexibility and, in some cases, simple architectures.

On the other hand Pytorch is a Deep Learning frame that has gained substantial popularity during the last few years. In particular, Pytorch experienced a 194% growth throughout 2019. Its imperative "Pythonian" style, easy-to-use modularity and rich ecosystem make Pytorch the go-to DL-frame for a lot of research institutions and companies.

With that in mind, in this presentation I will show how to build a simple Wide & Deep model with Pytorch and how to use it for tabular data.

Bio: Javier Rodriguez Zaurin is a theoretical physicist with a background in astrobiology. He is currently working as a private consultant in industry, on projects involving recommendation systems in fashion and retail or fake news detection, among others.

** Introducing the AI lab at the British Antarctic Survey
** By Anita Faul, British Antarctic Survey

With support from the Alan Turing Institute the British Antarctic Survey has established an AI lab. The applications of AI in environmental sciences are many and varied, including basics such as data cleansing, change point and anomaly detection and extending to wildlife monitoring from space and climate modelling. The talk will give an overview and delve deeper into new algorithmic approaches to detecting and monitoring icebergs from space in radar satellite images.

Bio: Anita Faul is a Data Scientist helping to bring Machine Learning to BAS. Before this she was a Teaching Associate, Fellow and Director of Studies in Mathematics at Selwyn College, University of Cambridge. Anita holds a PhD in mathematics from Cambridge University.