mlsanityData to 7 Oct 2026

nn2poly: An R Package for Converting Neural Networks into Interpretable Polynomials

arXiv 2406.01588 ↗First posted 3 Jun 2024cs.LG cs.AI stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

The nn2poly package provides the implementation in R of the NN2Poly method to explain and interpret feed-forward neural networks by means of polynomial representations that predict in an equivalent manner as the original network.Through the obtained polynomial coefficients, the effect and importance of each variable and their interactions on the output can be represented. This capabiltiy of capturing interactions is a key aspect usually missing from most Explainable Artificial Intelligence (XAI) methods, specially if they rely on expensive computations that can be amplified when used on large neural networks. The package provides integration with the main deep learning framework packages in R (tensorflow and torch), allowing an user-friendly application of the NN2Poly algorithm. Furthermore, nn2poly provides implementation of the required weight constraints to be used during the network training in those same frameworks. Other neural networks packages can also be used by including their weights in list format. Polynomials obtained with nn2poly can also be used to predict with new data or be visualized through its own plot method. Simulations are provided exemplifying the usage of the package alongside with a comparison with other approaches available in R to interpret neural networks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 59 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

20 of 59 references.

References · 20

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  5. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  6. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  7. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  8. 2017Opening the Black Box of Deep Neural Networks via Informationcited by 494
  9. 2019The Shapley Taylor Interaction Indexcited by 143
  10. 2022Faith-Shap: The Faithful Shapley Interaction Indexcited by 68
  11. 2020Deep Polynomial Neural Networkscited by 63
  12. 2022From Shapley Values to Generalized Additive Models and backcited by 59
8 more
  1. 2018DALEX: explainers for complex predictive modelscited by 28
  2. 2021On Expressivity and Trainability of Quadratic Networkscited by 19
  3. 2018Explanations of model predictions with live and breakDown packagescited by 17
  4. 2020NeuralSens: Sensitivity Analysis of Neural Networkscited by 14
  5. 2021Towards a mathematical framework to inform Neural Network modelling via Polynomial Regressioncited by 6
  6. 2021NN2Poly: A polynomial representation for deep feed-forward artificial neural networkscited by 3
  7. 2023cito: An R package for training neural networks using torchcited by 2
  8. 2023Statistical inference using machine learning and classical techniques based on accumulated local effects (ALE)cited by 2

Built on by

Not cited yet.