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

[ICLR 2026] Official implementation of "SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction"

OWL Class Expressions Learning in Python

ZeroC is a neuro-symbolic method that trained with elementary visual concepts and relations, can zero-shot recognize and acquire more complex, hierarchical concepts, even across domains

[npj Digital Medicine'24] Aligning Knowledge Concepts to Whole Slide Images for Precise Histopathology Image Analysis

[AAAI 2024] ConceptBed Evaluations for Personalized Text-to-Image Diffusion Models

[ICLR 2025 Spotlight] This is the official repository for our paper: ''Enhancing Pre-trained Representation Classifiability can Boost its Interpretability''.

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

[MICCAI 2025 Young Scientist Award] Official implementation of "Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image Classification"

The Codebase for Causal Proxy Model

Learning to Infer Generative Template Programs for Visual Concepts -- ICML 2024

OntoSample is a python package that offers classic sampling techniques for OWL ontologies/knowledge bases. Furthermore, we have tailored the classic sampling techniques to the setting of concept learning making use of learning problem.

Official implementation of ICLR 2023 paper "A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics"

Library for hierarchical concept composition and reasoning

Implementation of FCA and Orcale-Learning for learning implication bases

EvoLearner: Learning Description Logics with Evolutionary Algorithms

EDGE, "Evaluation of Diverse Knowledge Graph Explanations", is a framework to benchmark diverse explanations (e.g., subgraph vs logical) for node classification in knowledge graphs.

Machine Learning Lab Programs in the curriculum

My Concept Learning algorithms implementation.

OWL explainable structural learning problem Benchmark Generator

Neuro-symbolic (NeSy) AI improves deep learning by integrating reasoning, prior knowledge, and constraints, making it in theory ideal for high-stakes applications. However, this promise depends on learning high-quality abstractions, which is challenging due to potential reasoning shortcuts. This project explores this problem in depth.

Concept length prediction for the ALC description logic.

Some of the most popular Machine Learning Concepts.

Implement Find-S algorithm which is used in concept learning

BottleNeck model modification for the survival analysis data

Rule-based supervised learning system built using the Find-S concept learning algorithm. Generates generalized hypotheses from structured datasets for deterministic inference. Implements explainable decision logic suitable for security and rule-driven workflows. Engineered as a lightweight, interpretable alternative to black-box ML models.

No description provided.

CSC3022H: Machine Learning Lab 2: Concept Learning

No description provided.

A concurrent implementation of the candidate elimination algorithm.