Neural Additive Models for PyTorch

An implementation of a simple Neural Additive Model. (Agarwal et al. 2020) in PyTorch. It is applied to the Iris dataset for classification and feature map visualization.

TODOs

• Implement the ExU
• Implement Binary Classification model structure
• Implement Regression model structure
• Implement a more general framework / classes / functions that perform the feature map visualization on arbitrary datasets