Course Syllabus
Course-PM
DIT821 Software Engineering for AI Systems lp1 HT19 (7.5 hp)
Course is offered by the department of Computer Science and Engineering
Contact details
- Examiner: Ivica Crnkovic, ivica.crnkovic@chalmers.se
- Lecturers
- Ivica Crnkovic, ivica.crnkovic@chalmers.se
- Lucy Lwakatare, llucy@chalmers.se
- Piergiuseppe Mallozzi, mallozzi@chalmers.se
- Guest lecturers - several AI and SE experts from academia and industry
- Daniel Langkilde, Annottell , Lecture and labs - Data Management (2019-10-9 and 2019-10-9)
- Jan Bosch ; Chalmers Software center, Talk, 12 Challenges in SE for AI (2019-10-14)
- Peltarion Company, lecturer (TBD) , Lecture and labs - 13 Advances in ML and DL(2019-10-16 -17)
- Gordana Dodig-Crnkovic, Chalmers, AI Ethics, Lecture and Workshop (2019-10-21)
- Supervisors
- Lucy Lwakatare, lucy.lwakatare@chalmers.se
- Piergiuseppe Mallozzi, mallozzi@chalmers.se
- Hugo Sica de Andrade, sica@chalmers.se
Student representatives
- Ranim Khojah
- Naief Jobsen
Course Evaluation Results
The results from the course evaluation questionnaire is now published.
Protocol: https://canvas.gu.se/courses/26427/files/folder/Course%20evaluation%20results?preview=1993233
Results: https://canvas.gu.se/courses/26427/files/folder/Course%20evaluation%20results?preview=1993231
Course purpose
The purpose of the course ins to give to students insights in basics of AI, its use, basics of software engineering of AI-based systems.
The course addresses issues relevant for software engineering for systems that use artificial intelligence (AI) techniques such as machine learning or large-scale parallel data processing. The course gives (a) an introduction of basic principles of AI, with emphasis on the principles and techniques used in machine learning (ML) and Deep Learning (DL), and (b) insights to support needed for successful implementation of AI systems. The course addresses the life cycle of AI systems: It includes data preparation (i.e. collecting data, data processing, storage, analysis), and building AI models by training and validation. It also discusses use of data, such as implications of using different data sets for the same goal, or using the same data set for different goals. Relevant software architectures and patterns are introduced and discussed in the context of a realistic application scenario. Finally, the ethical considerations in using data and providing automatically-created solutions are discussed.
Schedule
Course literature
There is a plenty literature in AI, Machine Learning and Deep Learning, available both as on-line literature, and as books.
Useful links:
- Elements of AI - very basic intro to AI
- Andrew Ng: Machine Learning MOOC at Coursera
Course design
The course consists of lectures and exercises, as well as supervision in connection to the exercises. The lectures will show the main principles, approaches and techniques with small, illustrative examples.
The exercises will exemplify the theories and principles given on the lectures. The exercise will includes hands-on tasks that state specific problems, and that will be solved using programming tools. Some of the exercises will require written reports.
- Lecture 0 - Course Introduction
- Lecture 1, 2 - Linear regression, Multiple linear regression
- Lecture 3, 4 - Polynomial regression, Classification I
- Lecture 5, 6 - Classification II, Unsupervised learning
- Lecture 7, 8 - Neural Networks, Deep Learning
- Lecture 9 - Reinforcement Learning
- Lecture 10 - AI Systems life cycle
- Lecture 11 - Data Management - Guest Lecture Annotell
- Lecture 12 - Challenges in SE for AI - Guest lecture Prof. Jan Bosch
- Lecture 13 - Advances in AI/ML/DL Lecture - Guest Lecture Peltarion
- Lecture 14 - Ethics and AI - Guest Lecture
Course Summary:
Date | Details | Due |
---|---|---|