UC3MAL10 Machine Learning

UC3MAL10 Machine Learning

  • Course description
    • NQF Level
      Bachelor's degree (Level 6 1. Cycle)
    • Area of Study
      Computing
    • Program of Study
      Applied Data Science
    • ECTS
      10
    • Campus
      Kristiansand, OnlinePLUS - Bergen, OnlinePLUS - Oslo, Online
    • Course Leader
      Isah Lawal
Introduction

Language of Instruction and assessment: English
May be offered on Campus and Online.
May be offered as a separate course.

Included in the following bachelor's degrees:

  • Applied Data Science
Course Aim(s)

The course aims to explore the approaches used to produce intelligent systems and gain a comprehensive understanding of many of the issues involved and give insight into the mechanisms that allow systems to learn. It will also investigate the deep learning approach to machine learning, introducing students to the concept of deep learning, common and developing algorithms, and associated technologies.

Course Learning Outcomes
Knowledge

The student has knowledge of

K1 the principles of machine learning.
K2 historical and emerging research and developments in the field of machine learning.
K3 the way in which automated processes can self-modify to effect changes in their performance and/or capabilities.
Skills

The student gain skills in

S1 design and evaluate representational schemes and the inference mechanisms that use them.
S2 ability to select and apply appropriate deep learning algorithms and technologies to practical domain-relevant challenges.
S3 critically interpret and evaluate the results of applying deep learning to data-driven problems.
S4 evaluate strengths, weaknesses of deep learning algorithms.
General Competence

The student can demonstrate

G1 the current importance and relevance of Machine Learning within the program of study.
G2 planning, implementing, evaluating and presenting the results of machine learning projects applied to specific problems.
G3 critical reflection on personal academic development and the application of machine learning within problematic situations.
Course Topics
  • Machine Learning
  • Introduction to Deep Learning
  • Applications of Deep Learning
Teaching Methods
  1. Teaching will be based on a hybrid-flexible approach. Instructor-led face-to-face learning is combined with online learning in a flexible course structure that gives students the option of attending sessions in the classroom, participating online, or doing both.
  2. All activities require active student participation in their own learning.
  3. Learning delivery methods and available resources will be selected to ensure constructive alignment with course content, learning outcomes and assessment criteria.
  4. Students will be taught using a mixture of guidance, self-study, and lecture material. Topics will be introduced in a series of weekly lectures. The guidance sessions will be directed practical exercises and reading in which students can explore topics with support from a teacher. This material will also require students to self-manage their time to ensure tasks are completed and the theory is fully understood. This will allow the students to fully engage with lectures and with their peers.
Resources and Equipment
  1. Learning resources are available in the LMS and include, but is not limited to:
    • literature and online reading material (essential and recommended)
    • streams, recordings and other digital resources, where applicable
    • video conferencing and communication platforms, if applicable
    • tools, software and libraries, where applicable
  2. Students must have access to an internet connection, and suitable hardware.
    • Accessing live streams and virtual laboratories requires a minimum broadband connection of 2Mbps (4Mbps recommended).
  3. Students working on their own laptop/computer are required to acquire appropriate communications software, e.g., webcam, microphone, headphones.
Prerequisite Knowledge

UC1DMA10 Discrete Mathematics, and UC2ADS10 Algorithms and Data Structures, or equivalent course(s).

Reading List

The reading list for this course and any additional electronic resources will be provided in the LMS.

Study Workload

250 nominal hours.
​Study workload applies to both Campus and Online students.

ActivityDuration
Teacher-led activity
24
Teacher-supported work
48
Self-study
178
Work Requirements

There are no mandatory assignments in this course.

Assessment Strategy

This course has two (2) exams contributing towards the overall and final grade of the course.

All exams must be assessed as passed to receive the final Course Grade.

Form of assessmentGrading scaleGroupingDuration of assessment
Online Exam
A-F
Report
A-F