Notebooks containing small toy problems aiding the understanding of Machine-Learning papers and book sections I am interested in. Generally these are small examples I reproduced from the papers I read in order to understand some of the interesting methods or concepts involved.
Hopefully some of these notebooks will evolve in research ideas or blog-posts, further developing these techniques.
List of paper notes:
-
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms <paper, notebooks>
-
Functional Variational Bayesian Neural Networks <paper, notebooks>
-
Gradient Estimation Using Stochastic Computation Graphs <paper, notebooks>
I plan using mostly Jupyter Lab and web-based vizualisation libraries such as Altair and Bokeh.
The environment in the root of this repo is currently sufficient to run all the notebooks. Specific environments and requirements could be later added in each project ief required.
conda env create -f environment.yml