#4: Andrew Ng, Structured Prediction / PyStruct

The official programme starts at 19:30. But you're welcome to join us at 19:00 already to have a chat and a drink with members.

1. Deep Learning: Machine learning and AI via large-scale neural networks (Andrew Ng, 40min)

The co-founder of Coursera, director of the Stanford AI Lab and general Machine Learning legend is going to join us (as well as three other European ML meetups) via video.

Update: Post your questions to Andrew here (http://www.google.com/moderator/#15/e=216d98&t=216d98.40&f=216d98.6eba0d)!

2. Deep Neural Nets Study Group (Marcel Ackermann, 10min)

Marcel is going to present the new Deep Learning study group (https://www.meetup.com/Coursera/Berlin-DE/1106822/) here in Berlin.

3. Kaggle contests (Abhishek Thakur, 5min)

4. Structured Prediction and PyStruct (Andreas Mueller, 45min)

Structured Prediction is a generalization of classification and regression to structured output spaces like sequences or trees. Unlike standard classification algorithms, structured prediction methods can exploit correlation in output variables.

The general form of a structured predictor f is f(x) = argmax_y g(x, y) where g is a compatibility function between an output structure y and the input x. Most methods for learning structured prediction are closely related to graphical models, which also have the constraint of g(x, y) being a probability distribution over y (in the conditional case).

The talk will give an introduction into structured prediction methods and the library PyStruct that implements many
common learning algorithms in python.

Have an interesting topic you want to talk about?

We're still looking for more presenters for our meetups. If you have an interesting topic you want to talk about, maybe between 15 and 45 minutes, then send a short abstract to daniel.nouri gmail.com. Thanks!