https://github.com/tomekkorbak/active-inference

A toy model of Friston's active inference in Tensorflow
https://github.com/tomekkorbak/active-inference

cognitive-science deep-learning free-energy tensorflow variational-inference

Last synced: 2 months ago
JSON representation

A toy model of Friston's active inference in Tensorflow

• Host: GitHub
• URL: https://github.com/tomekkorbak/active-inference
• Owner: tomekkorbak
• Created: 2017-05-21T16:13:44.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2017-07-28T21:52:25.000Z (over 7 years ago)
• Last Synced: 2024-10-03T12:35:23.005Z (3 months ago)
• Topics: cognitive-science, deep-learning, free-energy, tensorflow, variational-inference
• Language: Jupyter Notebook
• Homepage:
• Size: 43.9 KB
• Stars: 39
• Watchers: 6
• Forks: 8
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# active-inference

An attempt at implementing a toy model of a simple cognitive agent minimizing its informational free energy through variational inference (as described by Karl Friston's Free Energy Principle). This model is highly inspired by [McGregor et al., 2015](https://arxiv.org/pdf/1503.04187.pdf).