2018
Introduction. Computational approach, perception as inference, representation, coding, why probabilities? – MB, 12 Feb
Knowledge representation. Formal systems, logic, probability theory – DN, 19 Feb
Probabilistic models. Probability calculus, graphical models, Bayesian inference, approximate inference – DN, 26 Feb
Bayesian behaviour – BT, 5 Mar
Computer lab, implementation of Bayesian inference problems – MB, 12 Mar
- Slides
- Jupyter notebooks
- C.M. Bishop: Pattern Recognition and Machine Learning, Chapter 9
Approximate inference II: Sampling. MCMC – BT, 19 Mar
Bayesian modelling of vision I. PCA, the Olshausen & Field model, Modelling correlations of filters, GSM – GO, 26 Mar
Measuring priors – BT, 9 Apr
Neural representation of probabilities. PPC, sampling hypothesis – GO, 16 Apr
Structure learning. Learning theory, automatic Occam’s razor, visual chunk learning – DN, 23 Apr
Decision making and reinforcement learning – MB, 7 May
Bayesian modelling of vision II. Higher-level vision – GO, 14 May
2017
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
- Slides
- em_hf.txt
- Probabilistic programming languages
- Stan
- C. M. Bishop: PRML – Mixture Models and EM
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
2016
Lecturers: Gergő Orbán, Mihály Bányai, Merse E. Gáspár and Dávid Nagy
Introduction. Computational approach, perception as inference, representation, coding, why probabilities? – MB, 8 Feb
Knowledge representation. Formal systems, logic, probability theory – DN, 15 Feb
Probabilistic models. Probability calculus, graphical models, Bayesian inference, approximate inference – DN, 22 Feb
Bayesian behaviour – MG, 7 Mar
Approximate inference I. Iterative estimation, mixture distributions, EM – MB, 16 Mar – 18:00, room 0-817
- Slides, em_hf.txt
- Probabilistic programming languages
- Stan
- C. M. Bishop: Pattern Recognition and Machine learning – Mixture Models and EM
Approximate inference II: Sampling. MCMC – MG, 21 Mar
Measuring priors – GO, 4 Apr
Neural representation of probabilities. PPC, sampling hypothesis – MG, 11 Apr
Bayesian modelling of vision I. PCA, the Olshausen & Field model, Modelling correlations of filters, GSM – GO, 18 Apr
Bayesian modelling of vision II. Higher-level vision – GO, 25 Apr
Structure learning. Learning theory, automatic Occam’s razor, visual chunk learning – DN, 2 May
Decision making and reinforcement learning – MB, 9 May
2015
Introduction. Computational approach, perception as inference, representation, coding, why probabilities? – MB, 9 Feb
Probabilistic models I. Knowledge representation, probability theory, graphical models – MB, 16 Feb
- Slides
- Videolecture about probabilistic graphical models by Sam Roweis
- C. M. Bishop: Pattern Recognition and Machine learning – intro to probability theory, directed graphical models
- MOOC about probabilistic graphical models by Daphne Koller, sections Introduction and Bayesian Network fundamentals are relevant
Probabilistic models II: Inference. Model inversion, density estimation, ML, MAP, approximate inference – DN, 23 feb
- Slides
- D. MacKay: Information Theory, Inference, and Learning Algorithms – inverse probability, entropy
- T. L. Griffiths, C. Kemp, J. B. Tenenbaum: Bayesian models of cognition- sections 1,2
Bayesian behaviour – MG, 2 Mar
Probabilistic models III: Sampling. MCMC – MG, 9 Mar
- Slides,
- Video Lectures by David MacKay 1, 2
- Hamiltonian Monte Carlo book chapter
Identification of priors – GO, 16 Mar
Bayesian modelling of vision I. Linear-Gaussian models, PCA, the Olshausen & Field model – GO, 23 Mar
Probabilistic models IV. Iterative parameter estimation ,mixture distributions, EM – MB, 30 Mar
- Slides, em_hf.txt
- C. M. Bishop: Pattern Recognition and Machine learning – Mixture Models and EM
Neural representation of probabilities. PPC, sampling hypothesis – MG, 13 Apr
Bayesian modelling of vision II. Modelling correlations of filters, GSM – MB, 20 Apr
Models of higher-level vision. Texture representation, slow feature analysis – GO, 27 Apr
Structure learning. Formal learning theory, automatic Occam’s razor, visual chunk learning – DN, 4 May