Training

Basics of Bayesian inference with case studies

Background in probability theory

Bayes rule for parameter estimation

Bayesian inference for inverse problems

Case studies: 

Signal Deconvolution

Computed Tomography 

Basic methods and tools for Bayesian computation

Background in probability theory

Bayes rule for parameter estimation

Bayesian inference for Machine Learning

Bayesian Computation:

Analytic computation for Gaussian case

Laplace Approximation

Variational Bayesian Approximation

Message Passing 

Inverse problems of medical imaging systems

Medical imaging systems (CT Scan, MRI, PET, SPECT, ...)

Basic Mathematics (Fourier, Radon, Hilbert, Able Transforms)

Classical methods of X-ray Tomography

General linear Inverse problems

Model Based Iterative Methods

Bayesian inference for Inverse problems

State-of-the-Art methods 

Big Data and Deep Learning for Healthcare applications

Interest in biomedical imaging and healthcare research is growing all around the world. 

Recently two machine learning fields, deep learning and big data, related to biomedical 

imaging and healthcare, have gained considerable attention from academia and IT communities. 

We are proposing three days on site training that covers these two important topics and 

their application in healthcare

Basics of Bayesian Machine learning

Basic Machine Learning problems 

Parametric modeling and estimation

Bayesian parameter estimation

Hierarchical models with hidden variables

Bayesian computational methods and tools

Analytic computation for Gaussian case

Maximum A Posteriori (MAP) and Expected A Posteriori (EAP)

Laplace Approximation, AIC and BIC

Variational Bayesian Approximation (VBA) and Expectation-Maximization (EM)

Message Passing (MP) and Approximate Message Passing (AMP) 

Case Study of Clustering and Classification 

Mixture models

Gaussian Mixture Models

Student-t Mixture Models 

s