Python talk night at MotherDuck

Join us for an exciting talk night at MotherDuck in Seattle's Eastlake neighborhood! Come hungry, food and beverages will be provided.

Agenda:

5:30-6pm: Doors open/networking

6-6:10pm: Opening remarks

6:10-6:35pm: Talk #1

6:35-6:50pm: Intermission

6:50-7:05pm: Lightning Talk

7:05-7:30pm: Talk #2

7:30-7:40pm: Closing remarks

After party to follow at Little Water Cantina (2865 Eastlake Ave E, Seattle, WA 98102)

What we'll do:

This event will feature the following presentations:

Talk #1: GraphNN with PyTorch for prediction of molecular properties

Speaker: Nick Buker

Description: This talk walks through building a molecular melting point predictor in Python, starting from string encodings of chemical structures and working up to graph neural networks. We'll cover how to use RDKit to extract molecular properties and how to represent molecules as graphs where atoms are nodes and bonds are edges each with their own embeddings. Graph Isomorphism and Graph Attention Networks built using PyTorch and PyTorch Geometric will be compared against linear regression and boosting baselines.

Lightning Talk: all([]) == True and any([]) == False

Speaker: Matt Drury

Description: The all and any functions reduce lists of booleans to singular truth values, they're pretty useful! At some point, everyone gets curious and throws them an empty list, and the results may seem counterintuitive. We justify the choices here as the correct ones by introducing a style of reasoning from "universal properties".

Talk #2: TBD

Speaker: TBD

Description: TBD

What to bring:

Since this is a talk format meetup, you don't need a computer.

All attendees are required to abide by the PuPPy Code of Conduct, you can read the Code of Conduct.

Building access:

Motherduck staff will have the front door open and will direct folks to the office which is located upstairs.