Master's thesis : Knowledge Inference and Knowledge Completion Methods using Neuro-Symbolic Inductive Rules

Implementation of a straight-through gradient wrapper to allow for discrete latent representations. Provides binary discretizer which maps hidden representations to {0, 1} and a learnable multi-value discretizer, which maps hidden activations to their closest value in a set of given size.

Code for "ELLEN: Extremely Lightly Supervised Learning For Efficient Named Entity Recognition" (LREC-COLING 2024)

The official repository for the PSYCHIC model

PyEDCR is a package providing error detecting and corrective rules into Python. Given a model, PyEDCR's goal is to recognize when it is incorrect based on a set of conditions and then correct the incorrect prediction.

Vertex-Enriched Graph Neural Network (VEGNN)

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

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

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

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

Tree Stack Memory Units

Holographic Reduced Representations

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

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

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

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

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

AIKA is a new type of artificial neural network designed to more closely mimic the behavior of a biological brain and to bridge the gap to classical AI. A key design decision in the Aika network is to conceptually separate the activations from their neurons, meaning that there are two separate graphs. One graph consisting of neurons and synapses…

[CVPR 2024] Neural Markov Random Field for Stereo Matching

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