Welcome to the tutorial repo on supercharging cognitive modeling workflow with simulation-based inference (SBI). For the simulation part, we will use the Sequential Sampling Model Simulators (SSMS) Package.
We will illustrate posterior amortization, likelihood amortization and focus on aspects of scientific workflows that can benefit from each. You will learn about the powerful BayesFlow and HSSM toolboxes and how to leverage both respectively to supercharge you cognitive modeling.
Check the official course website for the schedule and more general information about the workshop.
All notebooks should be runnable directly via colab and this is the preferred mode of interaction with the tutorial material.
If you rather have a local setup, the instructions below should help you get started.
You can either clone the repository (if you're familiar with Git) or download it as a ZIP.
git clone https://github.com/your-username/hssm-bayesflow-workshop.git
cd hssm-bayesflow-workshop
- Click the green "Code" button
- Select "Download ZIP"
- Extract the ZIP file and navigate into the folder
This repository includes a pyproject.toml
file for easy dependency management with uv
. If you have uv
installed, you can set up the environment with:
# Install uv if you don't have it
curl -LsSf https://astral.sh/uv/install.sh | sh
# Create and activate a virtual environment with all dependencies
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install dependencies
uv pip install -e .
Make sure to install BayesFlow and SSMS for the Python version you use for this workshop:
pip install bayesflow ssm-simulators
You can also install conda and install the packages from an environment you create for the workshop materials.