lunduniversity.lu.se

AI Lund

An open network for research, education and innovation in the area of Artificial Intelligence at Lund University

Denna sida på svenska This page in English

AI & ML related courses at Lund University

Listed below are some AI and ML related basic courses given at Lund University. Some of them are only given to students in certain educational programs. Please also check out previous and planned courses at the COMPUTE research school.

 

 

Applied Machine Learning (EDAN95)

To give an introduction to several subdomains of machine learning and to give an orientation about fundamental methods and algorithms within these domains. To convey knowledge about breadth and depth of the domain.

7.5 credits

Next occasion: Autumn 2019

Details, entry requirements etc: Swedish | English

Course web: http://cs.lth.se/edan95/

Artificial Intelligence (EDAP01)

To give an introduction to several subdomains of artificial intelligence and to give an orientation about fundamental methods within these domains. To convey knowledge about breath and depth of the domain.

7.5 credits

Next occasion:  Spring 2020

Details, entry requirements etc: Swedish | English

Course web: http://cs.lth.se/edap01/

Artificial Neural Networks and Deep Learning (FYTN14)

Deep learning and artificial neural networks have in recent years become very popular and led to impressive results for difficult computer science problems such as classifying objects in images, speech recognition and playing Go. This course gives an introduction to artificial neural networks and deep learning, both theoretical and practical knowledge.

7.5 credits

Next occasion:  Autumn 2019

Details, entry requirements etc: Swedish | English

Course web: http://home.thep.lu.se/~mattias/teaching/fytn06/

Bioinformatics: Bioinformatics and Sequence Analysis (BINP11)

Bioinformatics, the application of computational methods to biological and biomedical problems, is a rapidly growing field. A large amount of data is being generated in the post genomic era through research in genomics, proteomics, and structural biology. It is therefore crucial that modern biochemists and biologists have knowledge of bioinformatics.

This course provides both a practical and a theoretical overview of database searching, sequence alignment, phylogenetic and gene prediction, and genome analysis. The practical exercises exemplify how computational methods can be applied to real-world investigations of problems of biomedical and biological relevance.

7.5 credits

Next occasion:  ----

Details, entry requirements: English

 

Bioinformatics Project (BINP35/BINP37/BINP39)

The course includes planning, implementation and presentation of a part of a research project. The project shall have a connection to the bioinformatics education.

7.5/15/30 hp credits

Details, entry requirements etc

  • Bioinformatics: Research Project 7.5 credits (5 weeks) BINP35 (pdf) 
  • Bioinformatics: Research Project 15 credits (10 weeks) BINP37 (pdf) 
  • Bioinformatics: Research Project 30 credits (20 weeks) BINP39 (pdf)

Computer Vision (FMAN85)

The aim of the course is to give an overview of the theory of and practically useful methods in computer vision, with applications within e.g. vision systems, non-invasive measurements and augmented reality. In addition the aim is to make the student develop his or her ability in problem solving, with and without a computer, using mathematical tools taken from many areas of the mathematical sciences, in particular geometry, optimization, mathematical statistics, invariant theory and transform theory.

6.0 credits

Next occasion: Spring 2020

Details, entry requirements etc: Swedish | English

Course web: http://www.maths.lth.se/matematiklth/personal/calle/datorseende19/ 

Image Analysis (FMAN20)

The main aim of the course is to give a basic introduction to theory and mathematical methods used in image analysis, to an extent that will allow the student to handle industrial image processing problems. In addition the aim is to help the student develop his or her ability in problem solving, both with or without a computer. A further aim is to prepare the student for further studies in e.g. computer vision, multispectral image analysis and statistical image analysis.

7.5 credits

Next occasion: Autumn 2019

Details, entry requirements etc: Swedish | English

Course web: http://www.ctr.maths.lu.se/course/newimagean/2019/

Legal Aspects on Artificial Intelligence (HARA30)

The course provides an introduction to legal aspects of Artificial lntelligence, Machine Learning and the Internet of things.
Students learn how to interpret and apply relevant legislation, and to identify legal issues, and independently assess current issues in the light of principles and legal practices.

7.5 credits

Next occasion: Autumn 2019

Details, entry requirements etc: English

Course web: har.lu.se/kurser/hara30

Language Technology (EDAN20)

In the past 15 years, language technology has considerably matured driven by the massive increase of textual and spoken data and the need to process them automatically. Although there are few systems entirely dedicated to language processing, there are now scores of applications that are to some extent "language-enabled" and embed language processing techniques such as spelling and grammar checkers, information retrieval and extraction, or spoken dialogue systems. This makes the field form a new requirement for the CS engineers.

The course introduces theories used in language technology. It attempts to cover the whole field from character encoding and statistical language models to semantics and conversational agents, going through syntax and parsing. It focuses on proven techniques as well as significant industrial or laboratory applications.

7.5 credits

Next occasion: Autumn 2019

Details, entry requirements etc: Swedish | English

Course web: cs.lth.se/edan20/

Linear and Logistic regression (MASM22)

Least squares and maximum-likelihood-method; odds ratios; Multiple and linear regression; Matrix formulation; Methods for model validation, residuals, outliers, influential observations, multi co-linearity, change of variables; Choice of regressors, F-test, likelihood-ratio-test; Confidence intervals and prediction. Introduction to: Correlated errors, Poisson regression as well as multinomial and ordinal logistic regression.

7.5 credits

Next occasion: Spring 2019

Details, entry requirements etc: Swedish | English

Course web: www.maths.lth.se/matstat/kurser/masm22/

Machine learning (FMAN45)

Machine learning is an essential topic for many research areas, and across multiple departments at LTH, including applied mathematics, automatic control, computer science, medical imaging, signal processing, and mathematical statistics. It brings forward novel methodologies with transformative potential in big data analysis, specifically in application areas like image understanding (computer vision, image analysis), indexing and web search engines, natural language processing, robotics, or data analytics. The past years have witnessed an explosion of large-scale fully trainable methodologies based on hierarchical processing within the emerging fields of deep learning and reinforcement learning. This development is now in full swing, generating new research results in areas as diverse as automatic translation or game playing, and is beginning to successfully address some of the most profound open problems of intelligent processing.

7.5 Credits

Next occasion: Spring 2019

Details, entry requirements etc: Swedish | English

Medical Image Analysis (FMAN30)

The main aim of the course is to give a basic introduction to theory and mathematical methods used in medical image analysis, to an extent that will allow the student to handle medical image processing problems. In addition the aim is to make the student develop his or her ability in problem solving, both with or without a computer. A further aim is to prepare the student for further studies and research in the border area between medicin and engineering

7.5 credits

Next occasion: Autumn 2019

Details, entry requirements etc: Swedish | English

Course web: http://www.ctr.maths.lu.se/course/medim/

Monte Carlo and Empirical Methods for Stochastic Inference (FMSN50/MASM11)

Simulation based methods of statistical analysis. Markov chain methods for complex problems, e.g. Gibbs sampling and the Metropolis-Hastings algorithm. Bayesian modelling and inference. The re-sampling principle, both non-parametric and parametric. The Jack-knife method of variance estimation. Methods for constructing confidence intervals using re-sampling. Re-sampling in regression. Permutations test as an alternative to both asymptotic parametric tests and to full re-sampling. Examples of mor complicated situations. Effective numerical calculations in re-sampling. The EM-algorithm for estimation in partially observed models.

7.5 credits

Next occasion: Spring 2020

Details, entry requirements etc: 

Course web: http://www.ctr.maths.lu.se/course/FMSN50MASM11/

Project in Applied Mathematics (FMAN40)

The aim of the course is to give the engineering student who is interested in mathematics the opportunity to independently extend his or her knowledge of mathematics as well as to give practice in written and oral communication. A continuation in the form of a small project of for example one of the courses Computer Vision, Image Analysis, and Medical Image Analysis.

3 credits

Next occasion: Autumn 2019 , Spring 2020

Details, entry requirements etc: Swedish | English

Course web: http://www.maths.lth.se/course/applmathproj/

Project in Computer Science (EDAN70) and Advanced Project in Computer Science (EDAN90)

The course is currently given in three instances each year (LP1, LP2 and LP4). At each course instance, projects within specific areas are offered:

  • Project in Language Technology.
  • Project in Compilers.
  • Project in Multicore programming.
  • Project in Intelligent Systems.

EDAN90 is similar to EDAN70, but has higher requirements on the oral presentation and written report, to follow academic standards within the subarea. To take EDAN90, you need to first have completed EDAN70. EDAN90 offers projects in the same areas as EDAN70.

7.5 Credits

Next occasion: Autumn 2019, Spring 2020

Details, entry requirements etc EDAN70: Swedish | English

Details, entry requirements etc EDAN90: Swedish | English

Course web: http://cs.lth.se/edan70/

Project in Mathematics (FMAN35)

The aim of the course is to give the engineering student who is interested in mathematics the opportunity to independently extend his or her knowledge of mathematics as well as to give practice  in written and oral communication. A continuation in the form of a small project of for example one of the courses FMAN55 Applied Mathematics, FMAN70 Matrix Theory or FMAN15 Nonlinear Dynamical Systems.

Next occasion: Autumn 2019

Details, entry requirements etc: Swedish | English

Course web: http://www.maths.lth.se/course/matproj/

Rättsliga aspekter på artificiell intelligens (HARH02)

Kursen ger en orientering avseende rättsliga aspekter som kan uppkomma vid användning av artificiell intelligens och maskininlärning inom olika branscher samt om föremål som kan styras eller utbyta data över internet (sakernas internet). Vissa frågor är relevanta för samtliga branscher, såsom till exempel säkerhet, ansvar, transparens och dataskydd. Andra rättsliga aspekter är mer ämnesspecifika. Kursen belyser och problematiserar även fördelar och nackdelar ur ett juridiskt perspektiv med att använda artificiell intelligens och maskininlärning.

Undervisningen består av föreläsningar och seminarier. Vid seminarierna kommer studenterna att få skilda problem presenterade. Dessa problem ska sedan lösas i mindre grupper och redovisas i slutet av seminariet. Under kursen ska studenten även individuellt och självständigt författa promemorior och muntligt redovisa dessa.

7.5 credits

Next occasion: Autumn 2019

Details, entry requirements etc: Svenska 

Course web: https://har.lu.se/kurser/harh02

Spatial Statistics with Image Analysis (MASM25/FMSN20)

Bayesian methods for stochastic modelling, classification and reconstruction. Random fields, Gaussian random fields, Kriging, Markov fields, Gaussian Markov random fields, non-Gaussian observationer. Covariance functions, multivariate techniques. Simulation methods for stochastic inference (Gibbs sampling). Applications in climate, environmental statistics, remote sensing, and spatial statistics.

7.5 credits

Next occasion: Autumn 2019

Details, entry requirements etc:  English (LTH),  Svenska (NF)

Statistics: Deep Learning and Artificial Intelligence Methods

This course presents an application-focused and hands-on approach to learning neural networks and reinforcement learning. It can be viewed as first introduction to deep learning methods, presenting a wide range of connectionist models which represent the current state-of-the-art. It explores the most popular algorithms and architectures in a simple and intuitive style.

7.5 credits

Next occasion:  November 2019

Details, entry requirements etc: Swedish