The course is included in these curricula and study modules
- Big data analytics 2016 - Big data analytics
- Big data analytics 2017 - Big data analytics
- Big data analytics 2018 - Big data analytics
- Big data analytics 2019 - Big data analytics
- Big data analytics 2020 - Big data analytics
- Big data analytics 2021 - Big data analytics - specialised professional studies
- Big data analytics 2022 - Big data analytics - specialised professional studies
- Big data analytics 2023 - Big data analytics - specialised professional studies
The course takes place in period
- 1 (2022-08-01 to 2022-10-23)
- 2 (2022-10-24 to 2022-12-31)
Level/category
Teaching language
English
Type of course
Compulsory
Cycle/level of course
Second
Recommended year of study
1
Total number of ECTS
5 cr
Competency aims
The aim of the course is that the student will be
able to apply machine learning models and create a
proper pipeline for prediction from static data.
Learning outcomes
At the end of the course, the student is expected to be able to understand and predict with data using
machine learning models. The student will be able to
select the proper model and metric based in the
nature of the problem and optimize its parameters
using pipelines with grid-search.
Course contents
The students learn to understand the bases of
predictive machine learning with static data.
The students understand how modeling is
performed and how to deal with problems of
classification and regression. The students
gain an understanding of how to create optimized
models able to escalate to production.
Prerequisites and co-requisites
Basic python programming skills, statistics and linear algebra are required. Introduction to Analytics course is also recommended. A good basis of calculus is recommended, but not required.
Recommended or required reading
Introduction to Machine Learning with Python A
Guide for Data Scientists by Sarah Guido,
Andreas Müller.
An Introduction to Statistical Learning with
Applications in R by Gareth James, Daniela
Witten, Trevor Hastie and Robert Tibshirani,
Springer.
The Elements of Statistical learning by
Trevor Hastie, Robert Tibshirani, Jerome
Friedman, Springer.
Deep Learning with Python by François Chollet,
Manning publications.
Study activities
- Lectures - 30 hours
- Individual- and group instruction - 15 hours
- Project- and production work/artistic activities - 30 hours
- Individual studies - 60 hours
Workload
- Total workload of the course: 135 hours
- Of which autonomous studies: 135 hours
- Of which scheduled studies: 0 hours
Mode of Delivery
Multiform education
Assessment requirements
To pass the course, the student should pass the
following examinations: Jupyter notebooks solving
a problem during the lectures and homeworks with
associated content.
Teacher
- Espinosa Leal Leonardo
- Majd Amin
- Scherbakov-Parland Andrej
Examiner
Espinosa Leal Leonardo
Home page of the course
Group size
No limit (29 students enrolled)
Assignments valid until
12 months after course has ended
Course enrolment period
2022-08-10 to 2022-09-06
Date | Time | Room | Title | Description | Organizer |
---|---|---|---|---|---|
2022-10-13 | 13:00 - 18:00 | D4110 | Machine Learning for Predictive Problems | (Zoom link: bit.ly/MLPP22-23) | Espinosa Leal Leonardo Scherbakov-Parland Andrej |
2022-10-14 | 14:00 - 18:00 | F363 | Machine Learning for Predictive Problems | (Zoom link: bit.ly/MLPP22-23) | Espinosa Leal Leonardo Scherbakov-Parland Andrej |
2022-11-03 | 13:00 - 18:00 | D4109 | Machine Learning for Predictive Problems | (Zoom link: bit.ly/MLPP22-23) | Espinosa Leal Leonardo Scherbakov-Parland Andrej |
2022-11-04 | 13:00 - 18:00 | D4109 | Machine Learning for Predictive Problems | (Zoom link: bit.ly/MLPP22-23) | Espinosa Leal Leonardo Scherbakov-Parland Andrej |
2022-11-10 | 13:00 - 18:00 | D4109 | Machine Learning for Predictive Problems | (Zoom link: bit.ly/MLPP22-23) | Espinosa Leal Leonardo Scherbakov-Parland Andrej |
2022-11-11 | 13:00 - 18:00 | D4109 | Machine Learning for Predictive Problems | (Zoom link: bit.ly/MLPP22-23) | Espinosa Leal Leonardo Scherbakov-Parland Andrej |