andrew-mcinerney/statnn: Interpreting Neural Networks From a Statistical Perspective
Extends exisitng neural network packages in R to have more statistically-based outputs. Allows for the calcualtions of p-values for neural network inputs, covariate-effect plots with their associated uncertainty, and display interpretable summaries. See McInerney and Burke (2023) "Feedforward neural networks as statistical models: Improving interpretability through uncertainty quantification" for more details. <arXiv:2311.08139>.
Getting started
Browse package contents
Package details |
|
|---|---|
| Maintainer | |
| License | GPL (>= 3) + file LICENSE |
| Version | 0.0.0.9000 |
| URL | https://github.com/andrew-mcinerney/interpretnn https://andrew-mcinerney.github.io/interpretnn/ |
| Package repository | View on GitHub |
| Installation |
Install the latest version of this package by entering the following in R:
|
