Deep Learning for Music Information Retrieval & Kaggle Galaxy Zoo Challenge

Excited to announce the May meetup where Sander (http://reslab.elis.ugent.be/sander) will talk about his research and his winning entry for Kaggle's Galazy Zoo Challenge (http://blog.kaggle.com/2014/04/18/winning-the-galaxy-challenge-with-convnets/).

See you there!

Dirk & Ali

• Start: 6:30PM

• 6:30-45: Community updates and upcoming courses

• 6:45-8:15: Talk and Q&A

• End: 8:15 PM

Venue

UCL (University College London)

Christopher Ingold Building (http://www.ucl.ac.uk/estates/roombooking/building-location/?id=067)

XLG2 Auditorium

20 Gordon Street

WC1H 0AJ, London

Deep Learning for Music Information Retrieval (MIR) & Kaggle Galaxy Zoo Challenge

Deep learning has become a very popular approach for solving speech recognition and computer vision problems in recent years. In this talk we'll explore two different, but related applications. One is feature learning for music information retrieval (MIR): how can we use deep learning techniques to learn features from musical audio signals that are useful for classification and recommendation? We'll look at a few different tasks and feature learning approaches.

The other is galaxy morphology prediction: by automatically classifying galaxies based on their shape, astronomers can come to new insights about their origin and their distribution in space. We'll take a closer look at the convolutional neural network that won the recently finished Galaxy Zoo Challenge on Kaggle.

Bio: Sander Dieleman is a PhD student in the Reservoir Lab of prof. Benjamin Schrauwen at Ghent University in Belgium. His main research focus is applying deep learning and feature learning techniques to music information retrieval (MIR) problems, such as audio-based music classification, automatic tagging and music recommendation.

Thanks to UCL for providing the venue and our sponsors Learning Connexions (http://learningconnexions.com/).