Course - Introduction to Machine Learning - TDT4172
Introduction to Machine Learning
Choose study yearNew from the academic year 2024/2025
About
About the course
Course content
The course gives a basic introduction to data analysis and machine learning. It covers the learning regimes of supervised and unsupervised learning thoroughly, and a light introduction to reinforcement learning and explanation methods for machine learning models. The course work is project driven with focus on applications, using Python and commonly used machine learning libraries.
Learning outcome
Knowledge: Fundamentals of machine learning with commonly used learning algorithms. Skills: Ability to analyse data sets, and train and evaluate machine learning models on data. Evaluate adequateness of learning regimes based on the data. General competencies: Understand the basic principles of data analysis and machine learning. Knowledge about the applicability and limitations of different contemporary learning algorithms.
Learning methods and activities
Lectures, self-study. Compulsory activity in the form of assignments, will be published during the semester. These must be passed to gain admittance to the final exam.
Restricted admission: This course is for 500 students only.
Compulsory assignments
- Mandatory assignments
Further on evaluation
Admission restriction: Only 500 students will be admitted. You must apply via Studentweb. Students who have the course as mandatory or elective in their study plan will be prioritized first.
If there is a re-sit examination, the examination form may be changed from written (multiple choice) to oral.
Specific conditions
Admission to a programme of study is required:
Applied Physics and Mathematics (MTFYMA)
Chemical Engineering and Biotechnology (MTKJ)
Civil Engineering (MTBYGG)
Computer Science (MIDT)
Computer Science (MTDT)
Cyber Security and Data Communication (MTKOM)
Cybernetics and Robotics (MITK)
Cybernetics and Robotics (MTTK)
Digital Infrastructure and Cyber Security (BDIGSEC)
Digital Infrastructure and Cyber Security (MSTCNNS)
Electrical Engineering (BIELEKTRO)
Electronics System Design and Innovation (MTELSYS)
Energy and the Environment (MTENERG)
Engineering and ICT (MTING)
Industrial Design Engineering (MTDESIG)
Industrial Economics and Technology Management (MTIØT)
Informatics (BIT)
Informatics (MSIT)
Logistics - Engineering (FTHINGLOG)
Marine Technology (MTMART)
Mathematical Sciences (BMAT)
Mechanical Engineering (MIPROD)
Mechanical Engineering (MTPROD)
NTNU School of Entrepreneurship (MIENTRE)
Natural Science with Teacher Education, years 8 - 13 (MLREAL)
Physics (MSPHYS)
Recommended previous knowledge
Some experience in Python programming, ability to use Jupyter Notebooks, basic and intermediate college mathematics, including calculus and linear algebra.
Course materials
Hands-on Machine Learning with Scikit Learn, Keras and Tensorflow, 2022, Aurelien Geron
Subject areas
- Computer and Information Science