PyData Helsinki Meetup #1 : The Kick-off Meetup (Online)

Welcome to the kick-off meetup of PyData Helsinki. We are delighted to invite you to our first virtual meetup where we will feature two amazing guest speakers to talk about interesting topics. Come ready to socialize with other attendees and hear great talks.

The event will be held on Google Meet and it will be recorded. Please make sure your mic is MUTED when you join the meeting.

Online meetup link: https://meet.google.com/tqu-whzm-vvg

Agenda:

• 6:00pm - 6:10pm : Greetings & Introduction
• 6:10pm - 6:35pm: Best Practices for Data Augmentation
• 6:35pm - 6:45pm: Q&A
• 6:45pm - 7:10pm: Explaining ML models in 2020
• 7:10pm - 7:20pm: Q&A
• 7:20pm - 7:30pm: Chichat & Closing

-------------------------------------------

# (Talk 1) Oguzhan Gencoglu: Best Practices for Data Augmentation

Data Augmentation plays a prominent role in improving the generalization performance of machine learning solutions. This talk will first introduce the scientific rationale behind data augmentation and then will delve into the best practices of its utilization with real-life examples in Python. Specific data augmentation techniques for computer vision, natural language processing, and time series problems will be discussed with relevant open-source libraries. Finally, test-time data augmentation and data augmentation in the context of algorithmic fairness will be covered.

Oguzhan Gencoglu is the Co-founder and Head of AI at Top Data Science, a Helsinki-based AI startup that provides AI development as a service. With his team, he delivered more than 70 machine learning solutions in numerous industries for the past 4.5 years. Before that, he used to conduct machine learning research in several countries including USA, Czech Republic, Turkey, Denmark, and Finland.

# (Talk 2) Denis Vorotyntsev: Explaining ML models in 2020

Interpreting a machine learning model is a crucial, yet often ignored part of a development cycle. Nowadays we have a bunch of tools that may serve this purpose, but when to use which? In this talk, I will present several questions that should be asked during the ad-hoc model interpretation. I will show how to answer them using ad-hoc interpretations tools: SHAP, LIME, PDP plots, additive models, and anchors.

Denis Vorotyntsev is a Senior Data Scientist at Oura. He builds models for improving well being and health tracking. In his free time, he writes about ML and DS in his blog.

-------------------------------------------

PyData is a community for developers and users of open-source data tools. PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. The PyData Code of Conduct governs this meetup.