forestry-labs/interpretability_sandbox: Model Distillation and Interpretability Methods for Machine Learning Models
Provides several methods for model distillation and interpretability for general black box machine learning models and treatment effect estimation methods. For details on the algorithms implemented, see <https://forestry-labs.github.io/distillML/index.html> Brian Cho, Theo F. Saarinen, Jasjeet S. Sekhon, Simon Walter.
Getting started
Browse package contents
Package details |
|
|---|---|
| Maintainer | Theo Saarinen <theo_s@berkeley.edu> |
| License | GPL (>=3) |
| Version | 0.1.0.14 |
| URL | https://github.com/forestry-labs/distillML |
| Package repository | View on GitHub |
| Installation |
Install the latest version of this package by entering the following in R:
|
