English   Danish

2024/2025  KAN-CDSCO2004U  Machine Learning and Deep Learning

English Title
Machine Learning and Deep Learning

Course information

Language English
Course ECTS 7.5 ECTS
Type Mandatory (also offered as elective)
Level Full Degree Master
Duration One Semester
Start time of the course Spring
Timetable Course schedule will be posted at calendar.cbs.dk
Study board
Master of Science (MSc) in Business Administration and Data Science
Course coordinator
  • Somnath Mazumdar - Department of Digitalisation (DIGI)
Main academic disciplines
  • Information technology
  • Statistics and quantitative methods
Teaching methods
  • Face-to-face teaching
Last updated on 12-09-2024

Relevant links

Learning objectives
Students should meet the following learning objectives:
  • Understand fundamental challenges of machine learning models (selection, complexity).
  • Detect strengths and weaknesses of machine learning models.
  • Design, implement, machine learning models and deep learning techniques for realistic applications.
  • Summarize application areas, trends, and challenges in machine learning.
  • Exhibit deeper knowledge and understanding of covered topics.
  • Reflect on critical awareness of methodological choices with written skills to accepted academic standards.
Course prerequisites
This course requires a fundamental understanding of:
1. Probability
2. Statistics
3. Python programming.
Prerequisites for registering for the exam (activities during the teaching period)
Number of compulsory activities which must be approved (see section 13 of the Programme Regulations): 2
Compulsory home assignments
Each assignment is max. 5 pages + appendix, written in a group of 2-4 students. The students have to get 2 out of 3 assignments approved to go to the exam.
Process:
1. Exam papers of compulsory assignments will be uploaded into Canvas.
2. Students will upload their reports.
3. Finally,  the feedback will ONLY be visible via Canvas.
Examination
Machine Learning and Deep Learning:
Exam ECTS 7,5
Examination form Oral exam based on written product

In order to participate in the oral exam, the written product must be handed in before the oral exam; by the set deadline. The grade is based on an overall assessment of the written product and the individual oral performance, see also the rules about examination forms in the programme regulations.
Individual or group exam Individual oral exam based on written group product
Number of people in the group 2-4
Size of written product Max. 15 pages
Write product should use the 7th Edition of APA style reference.
Assignment type Project
Release of assignment An assigned subject is released in class
Duration
Written product to be submitted on specified date and time.
20 min. per student, including examiners' discussion of grade, and informing plus explaining the grade
Grading scale 7-point grading scale
Examiner(s) Internal examiner and second internal examiner
Exam period Summer
Make-up exam/re-exam
Same examination form as the ordinary exam
Students can submit the same project or they can choose to submit a revised project.
Course content, structure and pedagogical approach

The course provides knowledge of various concepts, techniques and methods related to machine learning and deep learning. More specifically, it contains 

  • Data pre-processing and exploratory data analysis 
  • Principles of unsupervised and supervised machine learning 
  • Unsupervised and supervised machine learning methods 
  • Strengths and weaknesses of dimensionality reduction algorithms, principal component analysis
  • Linear models for regression and classification 
  • Neural Networks: feed-forward neural networks, backpropagation, convolutional neural networks
  • Deep Learning: deep feed-forward networks, regularization for deep learning, optimization for training deep models, application of deep learning.
  • Ethical issues in machine learning and deep learning.

 

Furthermore, the course provides the students with practical hands-on experience in machine learning using open-source libraries such as scikit-learn. After completing the course, the students will be able to apply and use various machine-learning techniques on real datasets.

Description of the teaching methods
The course consists of lectures, exercises, and mandatory assignments. The lectures will ONLY be delivered offline and the hands-on exercise sessions will be conducted on campus. There will be teaching assistant(s) providing technical support for the hands-on exercise sessions.

The presented theories, concepts and methods should be applied in practice in the exercise sessions. The students will work on the mandatory assignments to consolidate their understanding of the concepts and the application of the concepts using the practical skills obtained from the hands-on exercises.
Feedback during the teaching period
During the hands-on exercises following each lecture, the students will receive help and feedback in solving the practical hands-on exercises from the teacher and the teaching assistant(s).
Student workload
Lectures 24 hours
Exercises 24 hours
Prepare to class 48 hours
Project work & report 100 hours
Exam and prepare 10 hours
Total 206 hours
Expected literature

Research articles, and other study materials will be uploaded (to the Canvas) during the course.

 

Primary Text Book: Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow. "O'Reilly Media, Inc.". ISBN: 9781492032649.

Last updated on 12-09-2024