Course syllabus

Tillämpad maskininlärning
Applied Machine Learning

EDAN95, 7,5 credits, A (Second Cycle)

Valid for: 2018/19
Decided by: PLED C/D
Date of Decision: 2018-04-03

General Information

Elective for: BME4, C4-pv, D4-bg, D4-pv, E4-bg, F4, F4-pv, Pi4, Pi4-pv
Language of instruction: The course will be given in English

Aim

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.

Learning outcomes

Knowledge and understanding
For a passing grade the student must

 

• display basic knowledge concerning theories and methods related to the following subdomains:
• unsupervised and supervised learning, classification and regression
• neural networks, including convolutional neural networks, recurrent neural networks and deep learning
• bayesian learning
• reinforcement learning
• support vector machines, decision trees, random forests, ensemble methods

Competences and skills
For a passing grade the student must

 

• complete a number of assignments based on problems related to some of the previously mentioned subdomains and demonstrating the ability to:
• evaluate and prepare the data
• select and train a model
• evaluate the outcome and fine-tune the model

 

Judgement and approach
For a passing grade the student must

 

• be able to judge suitability of a given machine learning method to a given problem,
• understand limitations of applicability of machine learning methods

 

Contents

 

• unsupervised and supervised learning, classification and regression
• neural networks, including convolutional neural networks, recurrent neural networks and deep learning
• bayesian learning
• reinforcement learning
• support vector machines, decision trees, random forests, ensemble methods
• hardware and software architectures for machine learning, parallelisation, use of GPUs

 

 

Examination details

Grading scale: TH - (U,3,4,5) - (Fail, Three, Four, Five)
Assessment: Written examination and assignments. The final grade of the course is based on the result of the written examination.

The examiner, in consultation with Disability Support Services, may deviate from the regular form of examination in order to provide a permanently disabled student with a form of examination equivalent to that of a student without a disability.

Parts
Code: 0118. Name: Written Examination.
Credits: 3. Grading scale: TH. Assessment: Written examination.
Code: 0218. Name: Assignments.
Credits: 4,5. Grading scale: UG. Assessment: To pass the course all the compulsory assignments must be approved. Details regarding the compulsory assignments will be found in the course program (syllabus) on the course web site. Contents: Assignments where some of the machine learning algorithms presented during lectures are implemented in order to give practical experience of difficulties related to, e.g., computational complexity, scalability and result interpretation.

Admission

Admission requirements:

• EDAA01 Programming - Second Course

The number of participants is limited to: 60
Selection: Credits remaining for the degree.

Reading list

• Kevin P. Murphy: Machine Learning, A Probabilistic Perspective. MIT Press, 2012, ISBN: 9780262018029. Reference text about machine learning.
• Ian Goodfellow, Yoshua Bengio, Aaron Courville: Deep Learning. MIT Press, 2016, ISBN: 9780262035613. Reference text on deep learning.
• Aurélien Géron: Hands-On Machine Learning with Scikit-Learn and TensorFlow, Concepts, Tools, and Techniques to Build Intelligent Systems. O'Reilly Media, 2017, ISBN: 9781491962299. Reference text about the applied part of the course.

Contact and other information

Course coordinator: Jacek Malec, jacek.malec@cs.lth.se
Course coordinator: Pierre Nugues, pierre.nugues@cs.lth.se
Course coordinator: Elin Anna Topp, elin_anna.topp@cs.lth.se
Course homepage: http://cs.lth.se/edan95
Further information: Detailed rules concerning the assignments will be found in the course web site.