Introduction to Deep Learning

What it is about

In this module you will learn the fundamentals and current methods of Deep Learning, with a special focus on neural networks and Convolutional Neural Networks. You understand theory (e.g. backpropagation, SGD, regularization) and acquire practical experience in training and optimizing network architectures, so you can solve simple applications such as digit recognition or image classification.

What you will be able to do

• Understanding of the theoretical concepts behind neural networks
• Knowledge of optimization methods such as SGD and backpropagation
• Ability to design, train and optimize CNNs
• Practical application of deep-learning frameworks (e.g. PyTorch)
• Carrying out simple computer-vision tasks (e.g. classification)

What the module consists of

• LectureConveying the theoretical aspects of neural networks and deep-learning architectures
• practical sessions/exercisesHands-on training: implementing, training and testing models; getting familiar with frameworks like PyTorch

Teaching method

• LectureExplanation of theory and methods, especially for computer-vision-related architectures
• practical exercisesGain experience through many training and testing runs as well as application to real problems