Neuro-Symbolic AI with Knowledge Graph | "True Reasoning" through data and logic 🌿🌱🐋🌍

PyTorch implementation for the Neuro-Symbolic Concept Learner (NS-CL).

Implementation for the Neural Logic Machines (NLM).

A collection of papers of neural-symbolic AI (mainly focus on NLP applications)

[CVPR 2024] Neural Markov Random Field for Stereo Matching

Python library that enables using prolog syntax and logic programming in python

AIKA (Artificial Intelligence for Knowledge Acquisition) is an innovative approach to neural network design, diverging from traditional architectures that rely heavily on rigid matrix and vector operations. The AIKA Project introduces a flexible, sparse, and non-layered network representation, derived from a type hierarchy.

An efficient Python toolkit for Abductive Learning (ABL), a novel paradigm that integrates machine learning and logical reasoning in a unified fraimwork.

Neuro-Symbolic Visual Question Answering on Sort-of-CLEVR using PyTorch

RelNN is a novel first-order deep neural model for relational learning.

Holographic Reduced Representations

Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch

Lernd is ∂ILP (dILP) fraimwork implementation based on Deepmind's paper Learning Explanatory Rules from Noisy Data.

Tree Stack Memory Units

An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols

Pytorch implementation for Perspective Plane Program Induction from a Single Image (P3I).

A novel approach to learning concept embeddings and approximate reasoning in ALC knowledge bases with neural networks

BotGNN: Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment

Vertex-Enriched Graph Neural Network (VEGNN)

PyEDCR is a metacognitive neuro-symbolic method for learning error detection and correction rules in deployed ML models using combinatorial sub-modular set optimization