NDAB16012U Modelling and Analysis of Data (MAD)
BSc Programme in Computer Science
BSc Programme in Physics
The purpose of the course is to provide a basic and broad introduction to the representation, analysis, and processing of sampled data. The course will introduce the student to statistical analysis, mathematical modelling, machine learning and visualization for experimental data. Examples will be taken from real-world problems, such as analysis of internet traffic, language technology, digital sound and image processing, etc. In addition, the course will provide an introduction to a programming tool suitable for data analysis (most likely one of the following: MATLAB, Python or R).
After the course the student should have the following knowledge, skills, and competences.
The student will have knowledge about statistical and data-analysis techniques including data-representation, filtering, modelling and estimation, and visualisation. This includes:
The central limit theorem
Descriptive statistical methods
Parameter estimation and confidence intervals
Likelihood functions and maximum likelihood estimation.
Least squares methods, linear regression
Simple models for classification
Presentation and validation of machine learning results
Multivariate statistics, Principal Component Analysis
Presentation of analysis results, including visualization by simple plotting
Introduction to programming tools for data analysis
The student will be able to:
Apply the least squares method for linear modeling and estimation.
Analyse sampled data by appropriate mathematical modelling methods.
Describe certain useful multivariate methods and their use, especially principal component analysis (PCA) and its use in dimensionality reduction.
Visualise low- and high-dimensional data by simple plots and images.
Implement simple data analysis and modeling methods.
Perform the analysis of experimental data using the methods learnt during the course and evaluate the results.
The student will be able to build and use simple statistical models, assess their relevance for solving concrete scientific problems, and quantify uncertainty about the drawn conclusions.
The student will be capable of performing basic data analysis tasks which include modelling, visualisation, and interpretation of the results.
The student will be able to describe the limitations of the used methods.
The student will be able to apply calculus tools, such as partial derivatives, gradients, and integrals.
The student will also become familiar with the analytical derivation of algorithms for data analysis.
See Absalon when the course is set up.
The course has a slightly changed curriculum compared to previous years.
- Practical exercises
- Theory exercises
There will be written feedback for the weekly assignments (comments via Absalon). For the final exam, the students can have individual oral feedback (there will be one feedback session that the students can attend).
- 7,5 ECTS
- Type of assessment
- Written assignment, 7 days7-day take-home-assignment, due on the last day of week 8 of the block.
- Exam registration requirements
Qualification for exam:
There are five to seven mandatory written assignments during the course, which may include programming tasks. All but one of these must be passed in order to be eligible for the exam.
- All aids allowed
- Marking scale
- 7-point grading scale
- Censorship form
- No external censorship
Multiple internal examiners.
If the student is not qualified for exam participation, qualification can be achieved by hand-in and approval of equivalent written assignments or course assignments that has not previously been approved. Hand-in deadline is two weeks prior to the exam.
The exam form is 20 minutes oral exam without preparation and in course curriculum. No aids allowed.
Criteria for exam assesment
See Learning Outcome.