Skip to content
/ pmlayer Public

Neural network layer to handle monotonicity constraints.

License

Notifications You must be signed in to change notification settings

IBM/pmlayer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Partially Monotone Layer

Partially monotome layer (pmlayer) is a library for neural network models. It provides several neural network layers to add monotonicity constraints on neural network models. Current implementation is available only for PyTorch.

Read the documentation to get started, and feel free to contact us for any inquiry.

Installation

You can install pmlayer by using the pip command:

pip install pmlayer

Citation

Please consider citing this paper.

H. Yanagisawa, K. Miyaguchi, and T. Katsuki, "Hierarchical Lattice Layer for Partially Monotone Regression," NeurIPS 2022.