Welcome to the 26th PyData Cambridge virtual meetup!

This is a virtual meetup. We will use zoom, login details published closer to the date.

Agenda

19:00 - Introduction
19:15 - "Picking the right loss function for your deep time series models" -- Isaac Godfried (CoronaWhy)
19:45 - "Notebook to production in 3 days - cutting the right corners." -- Daniel Roythorne
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

** Picking the right loss function for your deep time series models **

Abstract: Deep learning has seen recent success in many time series forecasting problems, however, choosing the right loss function remains crucial to getting your model to converge properly and perform well on the test set. In this talk I will survey different loss functions and their impact on different model's performance. We will also discuss which evaluation metrics might be most important to look at in an industry setting.

Bio: Isaac Godfried is a deep learning researcher with a focus on applying deep learning to real world problems. He has utilized modern machine learning techniques to forecast retail demand in stores, river flows, job supply/demand, and patient length of stay. He is also the creator and maintainer of flow-forecast, a deep learning for time series library built in PyTorch.

** Notebook to production in 3 days - cutting the right corners.**
Abstract: TBA