Official course description:
Full info last published 12/05-21

Applied Artificial Intelligence (Summer University)

Course info
Language:
English
ECTS points:
7.5
Course code:
KGAPARI1KU
Participants max:
50
Offered to guest students:
yes
Offered to exchange students:
no
Offered as a single subject:
no
Programme
Level:
MSc. Master
Programme:
MSc in Games
Staff
Course manager
Postdoc
Teacher
PhD student
Course semester
Semester
Forår 2021
Period
Summer 2021
Start
12 July 2021
End
27 August 2021
Exam
Exam type
ordinær
Internal/External
ekstern censur
Grade Scale
7-trinsskala
Exam Language
GB
Abstract
In this course, the students learn how to evaluate, design and prototype products based on latest artificial intelligence technologies.
Description

Artificial intelligence driven technology is becoming a central part of an increasing number of products, ranging from self-driving cars, to home assistants. Being able to design products based on this technology and evaluate their impact is a complex skill that requires knowledge if the inner working of different artificial intelligence algorithms and the ability to experiment with them.

While maintaining a product centric perspective, this course aims at giving the students the ability to understand the different mechanisms at the basis of modern artificial intelligence and use this knowledge to design and evaluate AI based applications.

NB: Please not that you can't take the course if you have already taken Introduction to Artificial Intelligence.

Formal prerequisites
  • understanding of basic computing concepts -- e.g. what is a process, what is a file or what is memory
  • understanding of fundamental principles of imperative programming -- e.g. variables, functions, parameters
  • experience in writing, building and running simple applications written in a scripting language -- e.g. python, processing, javascript
Intended learning outcomes

After the course, the student should be able to:

  • formulate hypotheses on implications of artificial intelligence technologies in new products
  • analyse the impact of AI on the potential end-user
  • describe the mechanisms that drive modern day artificial intelligence
  • compare multiple algorithms and identify the most appropriate for a given application
  • identify advantages and limitations of artificial intelligence algorithms
  • compile simple prototypes based on pre-existing library to experiment with AI methods
Learning activities

The course consists of exercises integrated into lectures with the teacher. The purpose of the lectures is to provide the context of the topics covered and available tools. During the lectures, the students will immediately get practical experience applying the tools to problems relevant to their exam hand-ins. There is a strong emphasis on problems and practices a student might come across in their professional environment.

Topics covered: 

1. Intro to AI theory and ML libraries.
2. Predicting Insurance cost using Regression and Deep Learning.
3. Image classification using Deep Learning.
4. Customer Segmentation with Clustering Methods.
5. Application of Natural Language Processing to sentiment analysis on Twitter.
6. Application of Natural Language Processing to topic modeling.
7. CONV-NET on CIFAR-10/Fashion-MNIST.
8. Intro to RL with application to Moon Lander.
9. Optimization - Genetic Algorithm, Hill Climbing, Evostrat.
10. CIFAR-10 image generation with GANs.
11. AI ethics.

Course literature

The course literature is published in the course page in LearnIT.

Ordinary exam
Exam type:
C: Submission of written work, External (7-point scale)
Exam variation:
C11: Submission of written work
Exam submisson description:
Students have to submit an individually made report with the code and the data attached

Time and date
Ordinary Exam - submission Fri, 13 Aug 2021, 08:00 - 14:00
Reexam - submission Fri, 27 Aug 2021, 08:00 - 14:00