Description: Description: Description: Description: Description: Description: Description: Description: Description: Description: Description: Description: Description: M:\public_html\accessories\aau_logo.gif            Deep Learning (Ph.D. Course)



Organizer: Associate Professor Zheng-Hua Tan, +45 9940-8686, zt@es.aau.dk, http://kom.aau.dk/~zt ,  B4-202, Fredrik Bajers Vej 7, 9220 Aalborg.

Lecturers:
Dong Yu, Principal Researcher, Microsoft Research, Redmond WA, USA, http://research.microsoft.com/en-us/people/dongyu/
Zheng-Hua Tan, Associate Professor, Aalborg University, Denmark

ECTS: 1
Period/time: Spring 2015
Place: Aalborg University

Thu. September 3 in the afternoon :
13:00-16:00     Frb 7A/4-108

Fri September 4 the whole day:
09:00-12:00     Frb 7C/2-209
13:00-16:00     Frb 7B/2-107

Description: Deep learning is a newly emerged area of research in machine learning and has recently shown huge success in a variety of areas. The impact on many applications is revolutionary, which ignites intensive studies of this topic.

During the past few decades, the prevalent machine learning methods, including support vector machines, conditional random fields, hidden Markov models, and one-hidden-layer multi-layer perceptron, have found a broad range of applications. While being effective in solving simple or well-constrained problems, these methods have one drawback in common, namely they all have shallow architectures. They in general have no more than one or two layers of nonlinear feature transformations, which limits their performance on many real world applications.

On the contrary, the human brain and its cognitive process, being far more complicated, have deep architectures that are organized into many hierarchical layers. The information gets more abstract while going up along the hierarchy. Interests in using deep architectures were reignited in 2006 when a deep belief network was shown to be trained well. Since then deep learning methods and applications have witnessed unprecedented success.

This course will give an introduction to deep learning both by presenting valuable methods and by addressing specific applications. This course covers both theory and practices for deep learning. Topics will include
    Machine learning fundamentals
    Deep learning concepts
    Deep learning methods including deep autoencoders, deep neural networks, recurrent neural networks, long short-term memory recurrent networks, and computational networks.
    Selected applications of deep learning
    Software and tools

Prerequisites:  Basic probability and statistics theory, linear algebra and machine learning.

Literature:
Li Deng and Dong Yu, Deep Learning: Methods and Applications, Now publishing, 2014.
Dong Yu and Li Deng, Automatic Speech Recognition - A Deep Learning Approach, Springer, 2014.