Logical Neural Networks
LNNs are a novel Neuro = Symbolic
framework designed to seamlessly provide key
properties of both neural nets (learning) and symbolic logic (knowledge and reasoning).
- Every neuron has a meaning as a component of a formula in a weighted real-valued logic, yielding a highly interpretable disentangled representation.
- Inference is omnidirectional rather than focused on predefined target variables, and corresponds to logical reasoning, including classical first-order logic theorem proving as a special case.
- The model is end-to-end differentiable, and learning minimizes a novel loss function capturing logical contradiction, yielding resilience to inconsistent knowledge.
- It also enables the open-world assumption by maintaining bounds on truth values which can have probabilistic semantics, yielding resilience to incomplete knowledge.
Quickstart
To install the LNN:
-
Install GraphViz and gmp (libgmp3-dev)
Tips for installing Graphviz
If you experience a "graphviz/cgraph.h" file not found error, try the following:# Using Conda conda install -c anaconda graphviz
Alternatively you can install the OS specific versions as follows:
# Ubuntu and Debian sudo apt-get install graphviz graphviz-dev
# MacOS brew install graphviz
# Windows / Powershell sudo apt-get install python3-dev graphviz libgraphviz-dev pkg-config
Tips for installing gmp
If you experience a "gmp.h" file not found error, try the following:
# MacOS brew install gmp env "CFLAGS=-I/usr/local/include -L/usr/local/lib" pip install pycddlib
# Windows Powershell / Anaconda conda install --channel conda-forge pygraphviz
# Ubuntu and Debian sudo apt-get install python3-dev graphviz libgraphviz-dev pkg-config sudo -H apt-get install libgmp-dev python3-dev
-
Make sure that the python version you use in line with our setup file, using a fresh environment is always a good idea:
conda create -n lnn python=3.9 -y conda activate lnn
-
Install the LNN as a library:
pip install git+https://github.com/IBM/LNN.git
Contribution
Contributions to the LNN codebase are welcome!
Please have a look at the contribution guide for more information on how to set up the LNN for contributing and how to follow our development standards.
Documentation
Read the Docs | Academic Papers | Educational Resources | Neuro-Symbolic AI | API Overview | Python Module |
---|---|---|---|---|---|
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
Citation
If you use Logical Neural Networks for research, please consider citing the reference paper:
@article{riegel2020logical,
title={Logical neural networks},
author={Riegel, Ryan and Gray, Alexander and Luus, Francois and Khan, Naweed and Makondo, Ndivhuwo and Akhalwaya, Ismail Yunus and Qian, Haifeng and Fagin, Ronald and Barahona, Francisco and Sharma, Udit and others},
journal={arXiv preprint arXiv:2006.13155},
year={2020}
}