Reproduce. Replicate. Reevaluate. The long but safe way to extend machine learning methods.

Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations

Hacking a Neural Network to understand what concepts the network learns in order to solve a logic task.

EmbedPVP: Embedding-based Phenotype Variant Predictor

Research code for heuristically hiding information for inference run on 3rd party systems (ICML 22)

Implementation of the paper: " Experimenting an Approach to Neuro-Symbolic RL"

A neuro-symbolic reasoner for the EL++ description logic.

program synthesis with neuro-symbolic differentiable interpreters

Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning

Code for the ICLR 2024 paper "How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data"

Demo for Neuro-Symbolic Agent (LOA)

Codebase for Neuro-Symbolic Continual Learning.

Holographic Reduced Representations

Self's foundational abstractions

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

[ACL 2024] The project of Symbol-LLM

Hrrformer: A Neuro-symbolic Self-attention Model (ICML23)

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

mOWL: Machine Learning library with Ontologies

PyTorch code for the RetoMaton paper: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022)