Bayesian Inference
For engineers and scientists who fit models to data.
What you will be able to do
- Explain Bayesian inference, and how it differs from maximum likelihood.
- Run Markov Chain Monte Carlo (MCMC) and check that it worked.
- Fit dynamic models, such as differential-equation models, with Bayesian inference.
- Infer model parameters from simulations when the likelihood is out of reach, using approximate Bayesian computation and neural density estimation.
Prerequisites
Python experience and a basic understanding of probability and statistics.
Outline
Duration: 1–2 days, on-site or remote, with exercises.
Four sessions.
- Introduction to Bayesian inference and MCMC
- Dynamic models with Bayesian inference
- Simulation-based inference: approximate Bayesian computation
- Simulation-based inference: neural density estimation
Sample materials
- Bayesian inference
- Bayesian inference in non-linear dynamic models: predator-prey model
- Likelihood-free inference: animal social networks
More in yoavram/ModelsPopBiol.
Related workshops
Contact
Tell me about your team and what you would like them to be able to do. A few lines are enough to start; I will reply to set up a scoping call.
Email Yoav yoav@yoavram.com