Short Description

This unit is designed to provide a comprehensive understanding of deep learning techniques in the first six weeks, ranging from foundational knowledge to the latest advancements in the field. Students will explore a variety of deep learning models. Through a hands-on approach, students will gain practical experience in implementing deep learning algorithms, including how to build, train, evaluate, and fine-tune deep learning algorithms to solve real-world problems. Students will also gain experience in training deep neural networks with Cloud GPU using services such as Google Colab. In the last two weeks, one of the most important aspects of intelligent behaviour, AI planning, will be introduced. Students will learn how to represent an AI planning problem and also practice solving it with a language called PDDL.

You’ll learn to:

• Demonstrate an understanding of a range of deep learning techniques, including MLP, CNN and RNN
• Demonstrate an understanding of how deep learning algorithms work, how to build them, and how to train them
• Apply deep learning techniques to solve real-life problems using deep learning libraries
• Solve AI planning problems with PDDL
   

Topics covered in this unit may include (but are not limited to) the following:  

• Multi-Layer Perception (MLP), a network inspired by the biological neural networks in our brains
• Convolutional Neural Network (CNN) for computer vision
• Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) for sequence data processing
• PDDL as an approach to solve planning problems