Module 412: Computational Inference (in years 2014 and 2015)

(:notitle:)

Module 412: Computational Inference

Module 412 develops Computational Inference: Bayesian inference for uncertainty quantification, stochastic modelling and MCMC sampling, advanced Monte Carlo strategies, imaging and machine vision.

Semester: 2

Recommended Preparation: Inverse Problems and Imaging module

Lecturer: Colin Fox. Room 503. Ph 4797806. colin.fox 'at' otago.ac.nz

Assessment: 30% assignments, 70% Exam

Resources:

• Lecture 1: Problem and Goals
  • Gareth Roberts' notes on Statistical Inference
• Lecture 2: Expectations
  • Adaptive rejection paper by Gilks Tan Best
• Lecture 3: MCMC basics
• Lecture 4: Algorithmic Efficiency
  • Ulli Wollf's UWerr MatLab code and documentation
• Lecture 5: Inverse Diffusion Problem
• Lecture 6: Image Reconstruction
• Lecture 7: Linear/Gaussian problems
  • John Bardsley's RTO paper
• Lecture 8: Counting objects
• Assignment 1:
  • Problem sheet Δ
  • Matlab code for diffusion problem: Main.m Δ heat.m Δ
• Assignment 2:
  • Problem sheet Δ
  • Matlab code for deblurring jupiter image: jupiter1.tif Δ jupiter.m Δ deconv1.m Δ
• Assignment 3:
  • Problem sheet Δ
  • Image of good and bad cells in Matlab mat format slide.mat Δ, or as slide.tif Δ. Matlab code makefake.m Δ that generated the image, and uses functions putgood.m Δ and putbad.m Δ.

Links:

Module 412 in 2015

Department of Physics 400-level information