Claude skills for Synalinks OSS

Neuro-Symbolic AI with Knowledge Graph | Logic Language for LLM 🌱🐋🌍

From idea to production in just few lines: Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices

A `Neural = Symbolic` framework for sound and complete weighted real-value logic

OriginTrail Decentralized Knowledge Graph network node

The code of NeurIPS 2021 paper "Scalable Rule-Based Representation Learning for Interpretable Classification" and TPAMI paper "Learning Interpretable Rules for Scalable Data Representation and Classification"

ChinaTravel: A Real-World Benchmark for Language Agents in Chinese Travel Planning

Neuro-Symbolic Reinforcement Learning: Logical Optimal Action (LOA), a novel RL with Logical Neural Network (LNN) on text-based games

Neuro-Symbolic Agentic Protocol

No description provided.

Holographic Reduced Representations

LEMMA: Logical Engine for Multi-domain Mathematical Analysis

NeuSyRE: A Neuro-Symbolic Visual Understanding and Reasoning Framework based on Scene Graph Enrichment

Normalizing flows for neuro-symbolic AI

A modular framework for Neuro-Symbolic reasoning driven by Large Language Models

Demo for Neuro-Symbolic Agent (LOA)

official repo for the NeurIPS 2022 paper "A Solver-Free Framework for Scalable Learning in Neural ILP Architectures"

Official codebase for the "A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts" benchmark paper.

Sem@K: Is my knowledge graph embedding model semantic-aware?

Codebase for BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts.

A neural network model builder, leveraging a neuro-symbolic interface.

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

Neuro-symbolic anomaly detection and complex fault diagnosis exemplified in the automotive domain.

The Compositional Agentic Architecture (CAA): A blueprint for building reliable, deterministic, and safe industrial AI agents.

Official website for the "A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts" benchmark paper

Turiya is a Self-Evolving Neuro-Symbolic AI that runs entirely on CPU. It learns autonomously from the web, builds a hybrid vector + logic knowledge base, performs reasoning using symbolic and neural methods, and evolves its world model through sleep-like consolidation cycles. A fully local, event-driven cognitive architecture.

ReOnto is a neuro-symbolic approach where we use ontologies and GNNs to extract relations from sentences.

Codebase for the paper "Generalized Reasoning with Graph Neural Networks by Relational Bayesian Network Encodings"

LLM-Generated Prolog Predicates with Embedded Justification Chains - Academic Research Paper (100+ pages, 97.5% correctness)

Lattice-preserving ALC ontology embeddings