Deep Neural Networks or so-called deep learning has attracted significant attention in the recent years. They have had a transformative influence on Natural Language Processing (NLP) and Artificial Intelligence (AI), with numerous success stories recent claims of superhuman learning performance in certain tasks. According to Young et al. (2017), more than 70% of the papers presented at recent NLP conferences made use of deep learning techniques. Interestingly, the concept of Neural Networks inspired researchers already over generations since Minky's famous book (cf. http://en.wikipedia.org/wiki/Society_of_Mind ). Yet again, this technology brings researchers to the believe that Neural Networks will eventually be able to learn everything (cf. http://www.ted.com/talks/jeremy_howard_the_wonderful_and_terrifying_implications_of_computers_that_can_learn ). This year we will focus on sequence learning with LSTM (long short-term memory) and similar recurrent network architectures and on their application to natural language processing tasks.

Dates & Rooms:
Wednesday, 8:30 - 10:00; Room: 0.154-115