Statistical Learning in the Nervous System

(in Hungarian, Statisztikai tanulás az idegrendszerben)


Spring semester, 2016/17

The course is listed at the following universities:

  • Eötvös University (ELTE), Neptun code: mv2n9044
  • Technical University (BME), PhD programmes, code BMETE47D088 (for technical reasons the couse is listed with the title ‘Magasabb szintű agyműködés modellezése’)
  • Technical University (BME), masters programmes, code BMETE47MC39
  • Pázmány University (PPKE), students can enroll to the class offered by ELTE in their own Neptun system
  • we welcome everyone else with personalized administrative procedures if needed


Lecturers: Gergő OrbánMihály Bányai, Balázs Török and Dávid Nagy
Time: Mondays, 4:10 pm – 5:40 pm
Location: ELTE Lágymányosi Campus, Northern Block (Északi Tömb) 0.87 Marx room

The course aims to cover a few topics in the functional description of the nervous system with special focus on statistical methods. Efficient methods for learning about visual data are described and the ways the nervous system implements these computations are also discussed. Materials of the course from previous years can be accessed here.


Exam dates:

  • 19 May, 9:00, BME T603 (with BMETE47D088 code only)
  • 30 May, 10:00, ELTE ÉT 2.105
  • 7 June, 10:00, ELTE ÉT 7.59
  • 12 June, 10:00, ELTE ÉT 7.59


List of exam topics

Homework results



Introduction. Computational approach, perception as inference, representation, coding, why probabilities?  – MB, 13 Feb


Knowledge representation. Formal systems, logic, probability theory – DN, 20 Feb


Probabilistic models. Probability calculus, graphical models, Bayesian inference, approximate inference – DN, 27 Feb


Approximate inference I. Iterative estimation, mixture distributions, EM – MB, 6 Mar


Bayesian behaviour – BT, 13 Mar


Approximate inference II: Sampling. MCMC – BT, 20 Mar


Neural representation of probabilities. PPC, sampling hypothesis – GO, 27 Mar


Measuring priors – BT, 3 Apr


Bayesian modelling of vision I. PCA, the Olshausen & Field model,  Modelling correlations of filters, GSM – GO, 10 Apr


Bayesian modelling of vision II. Higher-level vision – GO, 24 Apr


Structure learning. Learning theory, automatic Occam’s razor, visual chunk learning – DN, 8 May


Decision making and reinforcement learning – MB, 15 May


Computational Neuroscience

(in Hungarian, Idegrendszeri modellezés)

Neptun: kv2n9o46
Fall semester, 2013/14.
Lecturers: Gergő Orbán, Balázs Ujfalussy and Zoltán Somogyvári.
Course material can be found at

The course focuses on basic principles of computational neuroscience: the biophysics of neurons; action potential generation, transduction, and transmission; simple networks of neurons, and their modifications by learning; and the ways the nervous system encodes and decodes information about the environment and about the body.