Deep learning is a branch of machine learning based on representation of data with complex representations at a high level of abstraction. These representations are achieved by a sequence of trained non-linear transformations. Deep learning methods have been successfully applied in many important artificial intelligence fields such as computer vision, natural language processing, speech and audio understanding as well as in bioinformatics. This course introduces the most important deep discriminative and generative models with a special focus on practical implementations. Part one introduces key elements of classical feed-forward neural networks and overviews basic building blocks, regularization techniques and learning procedures which are specific for deep models. Part two considers deep convolutional models and illustrates their application in image classification and natural language processing. Part three considers sequence modelling with deep recurrent models and illustrates applications in natural language processing. Finally, part four is devoted to generative deep models and their applications in vision and text representation. All concepts are followed with examples and exercies in a modern dynamic language (e.g. Python, Lua, Julia). Most exercises shall be implemented in a suitable deep learning application framework (e.g. Tensorflow and Torch).
Learning Outcomes

•     Explain advantages of deep learning with respect to the alternative machine learning approaches.
•     Distinguish techniques which enable successful training of deep models.
•     Explain application fields of deep discriminative and generative models.
•     Distinguish kinds of deep models which are appropriate in supervised, semi-supervised and unsupervised applications.
•     Apply deep learning techniques in understanding of images and text.
•     Analyze and evaluate the performance of deep models.
•     Design deep models in a high-level programming language.

Type of methodology: Combination of lecture and hands-on

Paid training activity for participants: Yes, for some only

Participants prerequisite knowledge: C/C++

Language: English and Croatian