• ABL Package
• • Installation
  • Example
  • Authors
  • NOTICE
  • To do list

ABL Package

This is the code repository of abductive learning Package.

Installation

Case a: If you develop and run abl directly, install it from source:

git clone https://github.com/AbductiveLearning/ABL-Package.git
cd ABL-Package
pip install -v -e .
# "-v" means verbose, or more output
# "-e" means installing a project in editable mode,
# thus any local modifications made to the code will take effect without reinstallation.

Case b (TO DO): If you use abl as a dependency or third-party package, install it with pip:

pip install abl

Example

• MNIST ADD - here
• Hand Written Formula - here
• Hand written Equation Decipherment - here

Authors

• Yu-Xuan Huang (Nanjing University)
• (Nanjing University)

NOTICE

They can only be used for academic purpose. For other purposes, please contact with LAMDA Group(www.lamda.nju.edu.cn).

To do list

• Improve speed and accuracy
• Add comparison with DeepProbLog, NGS,... (Accuracy and Speed)
• Add Inference/Abduction example with FOL engine (e.g., Prolog)
• Add zoopt optimization
• Rearrange structure and make it a python package
• Documents