Introduction to Deep Learning

given by Dr. Sebastian Stober

Over the last decade, so-called “deep learning” techniques have become very popular in various application domains such as computer vision, automatic speech recognition, natural language processing, and bioinformatics where they produce state-of-the-art results on various challenging tasks. Most recently, deep neural networks even succeeded in mastering the game of go by just playing against themselves.

A crucial success factor of deep neural networks is their ability to learn hierarchies of increasingly complex features from raw input data. Such representations often outperform traditionally hand-crafted features that require expensive human effort and expertise. But they do not come as a free lunch. Designing and training deep neural networks such that they actually learn meaningful and useful feature representations of data is an art itself.

This course offers an introduction to the most important concepts, common training approaches and network architectures such as convolutional and recurrent neural networks - thus enabling participants to follow the deep learning literature in their field and taking first steps towards applying these techniques for their own research as well. Additionally, many references to further reading will be provided as well as programming exercises as an opportunity to gradually gain practical experience.