Skip to content
Formulating active learning as self-teaching
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
figures
models
notebooks
old_models
tests
.gitignore
README.md
__init__.py
run_example.py
run_simulations.py

README.md

Self-teaching

Code associated with:

Yang, S. C-H., Vong, W.K., Yu, Y., & Shafto, P. A unifying computational framework for teaching and active learning (submitted)

Directory structure

  • models: Contains the different models (active learning, teaching and self-teaching) used in the simulations
  • notebooks: Contains various jupyter notebooks with worked examples
  • old_models: Original matlab code of Pat's original pedagogical sampling model for the causal graph task and unused models
  • simulations: Code to run simulations (currently only self-teaching for the concept learning task)
  • tests: Directory for test code
  • run_simulations.py: Main file to run the simulations and generate the figures from the paper

Running the code

To run the simulations and produce the figures in the paper:

python run_simulations.py

To run the tests:

pytest

The tests require pytest on your machine, which can be installed with the following:

pip install -U pytest
You can’t perform that action at this time.