International Summer School on Deep Learning in Image Analysis – Københavns Universitet

International Summer School on Deep Learning in Image Analysis

Deep Learning

Deep learning is a set of algorithms in machine learning that attempt to model high-level abstractions in data by using architectures composed of multiple non-linear transformations. This contrasts to the standard ‘shallow’ approach where hand-crafted features are combined with a machine learning algorithm for the task at hand. Applications of deep learning include numerous problems in vision, speech, audio, or natural language processing. The best performing contenders on several benchmark data sets are deep leaning methods, and also mayor companies like Google, Microsoft, or Facebook are exploiting deep learning in their research and products.

Scientific content

The summer school will consist of 5 days of lectures and practical sessions with hands-on exercises. Students will obtain 3 ECTS for participation. Students should bring a poster presenting their research field (preferably with an angle towards deep learning). All other participants are highly encouraged to do so as well.

Registration

Cost for registration is DKK 4000. This includes accommodation, food, bus travel from Copenhagen and back, plus great social activities the whole week. For PhD students from DIKU costs will be covered by the Imaging and Machine Learning research school (IMLRS). Others should pay from their own grant(s). In case this is not possible the faculty will cover the fee for the members of the image group. The deadline for registration for participants from DIKU/DTU is 19 April 2014. After 19 April registration will be open for externals as well. We have room for only 70 participants. For more details on the registration see http://deep-learning.compute.dtu.dk/?page_id=12

More details can be found on http://deep-learning.compute.dtu.dk/