Introduction to Practical Machine Learning, 2 credits

Main field of study

Course level

Advancement level

Course offered for

• Master of Science in Computer Science and Engineering

Prerequisites

Mathematical analysis, linear algebra, statistics, programming in Python.

Intended learning outcomes

The overall aim of the course is to provide an introduction to machine learning with a focus on implementing and using models based on neural networks. The course will provide skills in implementing basic deep learning models in a dedicated software library.

After completion of the course, the student should be able to:

1. Use basic concepts and methods in machine learning to formulate, structure, and solve practical problems.

2. Construct basic models for classification and regression.

3. Implement basic neural network-based machine learning models in Python using a deep learning framework and fit these to training data.

4. Use pre-trained machine learning models and analyze their performance.

Course content

This course offers a gentle introduction to machine learning with a focus on implementing and using models based on neural networks. This includes: unsupervised and supervised learning; regression and classification; model training, selection, and evaluation; neural networks; convolutional neural network; deep learning; machine learning operations; application of the methods to real data. The course will provide skills in implementing basic deep learning models in a dedicated software environment, including support for GPU acceleration and automatic di􀆯erentiation, which are central
features for practical implementation of deep neural networks.

Teaching and working methods

The teaching consists of lectures and computer labs. Lectures are used to introduce basic concepts and theory that the students then use in practical problem solving within the computer labs. The computer labs also introduce the students to a deep learning framework (e.g., PyTorch). 

Examination

Grades

Department