1st lecture - What is AI?

• pre-reading Darwiche (see Literature) and videos
• post-module assignment 1:
  • critical short-essay 1-2 pages
  • individually, submit via Learn

2nd lecture - Introduction to Neural Networks and Deep-learning

• pre-reading Rashid part I

3rd - Deep learning frameworks in Python and business applications - part 1

4th - Deep learning frameworks in Python and business applications - part 2

• critical comparison of Deep Learning (blackbox AI) with explainable ML methods such as decision trees
• post-module assignment 2:
  • ML problem solved in NN/DL
  • dataset assigned by lecturer
  • submit via Learn

5th - lecture - Model-based AI/Hybrid AI and their business applications - part 1

6th - lecture - Model-based AI/Hybrid AI and their business applications - part 2

• compare with traditional methods for optimisation
• post-module assignment 3:
  • time-tabling case, scheduling or resource allocation problem to be solved with ASP
  • dataset assigned by lecturer
  • submit via Learn

Before final unit: submit all assignments in written form, via Learn

7th - Presentations of projects

• 10 min presentation of assignment 2 or 3, chosen by lecturer
• via MS Teams
• post-module assignment:
  • feedback to one of the presentations, assigned by lecturer
  • invididually or in groups of two, as in assignments 2 and 3
  • 1-2 pages
  • submit via Learn

Assignments 2 and 3:

• motivation and description of the case
• description of data
• solution and code
• max 5 pages excl. code.
• in groups of two, or individually, your choice

Evaluate and apply selected methods in current machine learning and other AI technologies for application in business scenarios

PI i.e. max 20% absence 

Lecture units on Connectionist and Deep Learning approaches, Symbolic AI, as well as Hybrid AI approaches.

Case studies from Business applications.

In total, three items of written work in the form of

• Assignment 1 as individual task, 10%
• Assignments 2 and 3 individually or as group projects, 40% each
• Assignment 4 individually or in groups of two as in assignments 2 and 3, 10 %

Python tutorial, e.g. on Datacamp: https://campus.datacamp.com/courses/intro-to-python-for-data-science