Python Talk: Towards Transfer Learning with Keras

PyData Munich is back with another accessible data science talk, this time at KI Labs!

Talk: "Solving Everyday Problems using Tech" by Nithish Raghunandanan

We give an overview of how we solve an everyday problem like controlling our office door from Slack. We take you on a tour of the solution powered by Raspberry Pi coupled with a bunch of free services.

Talk: "Towards Transfer Learning with Keras" by Cameron Beebe

Transfer learning is when we use a trained model to make predictions or inferences in a new domain, which is outside the scope of the original model. I will present theoretical and practical motivations for utilizing transfer learning in data science, detailing some pitfalls I have encountered trying to implement the theory of transfer learning in practice. As an example, we will see some of the ways transfer can be achieved across neural network models in Keras.

Schedule:

• 18:30 Doors Open
• 19:00 Welcome to PyData Munich
• 19:10 Talk by Nithish Raghunandanan (KI Labs)
• 19:50 Talk by Cameron Beebe: "Towards Transfer Learning with Keras"
• 20:40: Pizza, Beer and Networking

Many thanks to KI Labs for hosting and sponsoring this event!

If you are interested in giving a talk or organizing an event, please contact one of the organizers (including myself: kalemanov@biochem.mpg.com)! If you are looking for inspiration for a talk topic or want to request one, please check out the ever-growing lists of topics here: https://docs.google.com/document/d/1wrdv27B7UGRJelbk8EQdHmBZ8uuO0I4q2JlJrsiCGlI/edit?usp=sharing