Doel & Inhoud Engels
The objective of the course is to provide students with: (1) theoretical knowledge of convolutional and recurrent neural networks, (2) practical skills for performing experiments with deep learning, (3) understanding ways to (pre-)process signals, images, and texts for data science applications in general and for deep learning specifically.
Specifics
Deep Learning revolutionized machine learning by yielding the best performances in a large variety of application domains such as: speech recognition, image recognition, object detection, drug discovery and genomics. This course provides students with the understanding and skills to apply deep learning to signals, images, videos and textual sources. The course includes a training to run deep learning algorithms on special hardware.
Recommended Prerequisites
Basic understanding of machine learning / data mining. Elementary Statistics
|
|
The lectures of the course start with a historical overview of deep learning. After a review of the formal basics, deep feedforward networks are explained in terms of (nonlinear) transformations and the backpropagation training procedure. Subsequently, the importance of regularization to prevent overfitting is explained and procedures for optimizing the induced model are outlined. Then, the notions of convolution and convolutional neural networks are explained. Sequence learning is addressed next by means of recurrent neural networks and their applications. This is followed by a review of the practical methodology of deep learning methods. Finally, applications are reviewed and recent scientific progress on the development of deep learning methods is discussed.
During skill classes, students are trained on applying the concepts addressed in the lectures.
Type of instructions
lab sessions; self study;
Type of exams
60% written exam, 40% practical assignment
Compulsory Reading
- Goodfellow, I., Bengio, Y. and Courville, A., Deep Learning, Cambridge MA: MIT Press, 2016.
The courses from the Data Science and Entrepreneurship program require specific prior knowledge. It is only possible to participate in this course if approved by the admission committee and if you are enrolled for the program. Please note that this course will be taught in Mariënburg, ‘s-Hertogenbosch (JADS).
|
 |
|