SUBJECT

Title

Applied Deep Learning

Type of instruction

lecture+practical

Level

Master

Faculty

Faculty of Informatics

Part of degree program

Credits

2+2+1

Recommended in

Semester 3

Typically offered in

Autumn semester

Course description

In this course practical problems are addressed with deep learning techniques. Architectures: auto-encoders, convolutional neural networks, recurrent neural networks, long short-term memory, residual networks, and highway networks. Image processing: image restoration and super-resolution, bounding boxes, objects, face, hand, body recognition. Speech processing: speaker identification, speaker de-identification, speech recognition and speech production. Motion and control: deep learning for motion via imitation, dynamic movement primitives. Deep methods for anomaly detection, optical flow, tracking, multi-modal tracking, information fusion and pattern completion.

Readings

Compulsory readings:

Ian Goodfellow and Yoshua Bengio and Aaron Courville: Deep Learning. MIT Press, 2016. Hardcover: ISBN: 9780262035613, eBook: ISBN: 9780262337434

Recommended readings:

Jason Brownlee: Applied Deep Learning in Python Mini-Course
Aurélien Geron: Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts,
Tools, and Techniques to Build Intelligent Systems O’Reilly Media, Inc. 2017. ISBN: 1491962291
Josh Patterson and Adam Gibson: Deep Learning: A Practitioner's Approach. O’Reilly Media, Inc. 2017. ISBN: 1491914254
Sayan Pathak, Roland Fernandez, and Jonathan Sanito, Deep Learning Explained, MOOC edX, https://www.edx.org/course/deep-learning- explained-microsoft- dat236x