After successful completion of this course, you will be able to:
- Understand basics and preliminaries of deep learning
- Understand modern deep learning techniques
- Understand scalability, efficiency and applications of deep learning
- Implement these techniques in Python/MxNet/Jupyter.
|
|
In this course, you will learn about the concepts, the context and the code all the way from the humble beginnings of deep learning to the recent deep learning revolution that has completely transformed artificial intelligence from science fiction to reality as you study topics such as:
- Linear neural networks and multilayer perceptrons
- Deep learning computation, (modern) convolutional neural networks, (modern) recurrent neural networks and attention mechanisms
- Optimization algorithms, computational performance and computer vision
by following the open source book Dive into Deep Learning in weekly lectures and working on practical assignments in weekly labs.
NB: This course is under development and its details are subject to change.
|
|
|
- SOW-BKI104 Calculus
- SOW-BKI124 Linear Algebra
- SOW-BKI131 Programming 1
- SOW-BKI132 Programming 2
- SOW-BKI137 Probability Theory
- SOW-BKI138 Frequentist Statistics
|
|
The course consists of practical assignments and a final exam. The assignments will be rated graded as ‘pass’ or ‘fail’. The course grade is determined by the final exam but a ‘pass’ is required for the practical assignments in order to participate in the exam.
|
|
|