Search programme

Syllabus for	Academic year 2019/2020 2018/2019 2017/2018 2016/2017 2015/2016
MVE440 - Statistical Learning for Big Data
Syllabus adopted 2015-02-11 by Head of Programme (or corresponding)
Owner: MPENM
7,5 Credits
Grading: TH - Five, Four, Three, Not passed
Education cycle: Second-cycle
Major subject: Mathematics
Department: 11 - MATHEMATICAL SCIENCES

Teaching language: English
Open for exchange students
Minimum participants: 3
Maximum participants: 100

Course module

Credit distribution

Examination dates

Sp1

Sp2

Sp3

Sp4

Summer course

No Sp

0115

Examination

7,5c

Grading: TH

7,5c

30 May 2016 pm M

am J

In programs

MPENM ENGINEERING MATHEMATICS AND COMPUTATIONAL SCIENCE, MSC PROGR, Year 2 (elective)

Examiner:

Professor  Rebecka Jörnsten

  Go to Course Homepage

Eligibility:

In order to be eligible for a second cycle course the applicant needs to fulfil the general and specific entry requirements of the programme that owns the course. (If the second cycle course is owned by a first cycle programme, second cycle entry requirements apply.)
Exemption from the eligibility requirement: Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling these requirements.

Course specific prerequisites

The prerequisites for the course are a basic course in statistical inference and MVE190 Linear Statistical Models. Students can also contact the course instructor for permission to take the course.

Aim

The course should give understanding of and training in techniques for statistical analysis of large data sets.

Learning outcomes (after completion of the course the student should be able to)

• demonstrate
  understanding of the key concepts and ideas concerning
  classification, clustering and dimension reduction.
• solve high-dimensional data analysis exercises and interpret the results of such analyses.

Content

• Overview
  of high-dimensional data analysis

• Classification:
  Bayes rule, discriminant analysis methods, nearest neighbor
  classifier, classification and regression trees.
• 
  Cost
  functions, greedy searches, gradient descent, cross-validation.
• 
  Logistic
  regression
• 
  Regularization
  methods. Sparse logistic regression, sparse discriminant analysis.
• 
  Ensemble
  methods: bagging, random projections, random forests.
  
• 
  Clustering:
  k-means, hierarchical clustering, model-based clustering, spectral
  methods.
• 
  Dimension
  reduction: PCA, canonical correlation, multi-dimensional scaling.
• 
  Special
  topics (subset of the following): networks and graphical models,
  sparse covariance estimation, network clustering and community
  detection, neural networks, matrix completion, collaborative
  filtering.
  
• Large-scale
  learning: stochastic searches, batch-methods, online learning.

Organisation

The teaching is organized with lectures, discussions, and reading assignments.

Literature

To be announced.

Examination

Oral and/or written examination.