Neuro-Symbolic Artificial Intelligence: Current Trends
arXiv:2105.05330
Abstract
Neuro-Symbolic Artificial Intelligence -- the combination of symbolic methods with methods that are based on artificial neural networks -- has a long-standing history. In this article, we provide a structured overview of current trends, by means of categorizing recent publications from key conferences. The article is meant to serve as a convenient starting point for research on the general topic.
arXiv commentunder review
References in corpus (14)
- Dynamic Memory Networks for Visual and Textual Question Answering
- Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
- Measuring abstract reasoning in neural networks
- Neuro-Symbolic Program Synthesis
- Dimensions of Neural-symbolic Integration - A Structured Survey
- Differentiable Reasoning over a Virtual Knowledge Base
- Learning Continuous Semantic Representations of Symbolic Expressions
- Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections
- Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering
- Learning Reasoning Strategies in End-to-End Differentiable Proving
- Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"
- Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base
- Neural Logic Reinforcement Learning
- Combining Symbolic Expressions and Black-box Function Evaluations in Neural Programs