28 May 2014Time: 2:00 - 3:00pm
Venue: BR 3.02 Bancroft Road Teaching Rooms Peter Landin Building London E1 4NSSander Dieleman, a PhD student at Ghent University, will present a seminar in BR 3.02 (the Bancroft Road building) on "Classifying music and galaxies with deep learning" at Queen Mary University of London, Mile End Road, London E1 4NS. Dieleman's presence is sponsored by the Persontyle Data Science Centre of Excellence.
Abstract: "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.