A Survey on Neural-symbolic Learning Systems
arXiv:2111.08164
Abstract
In recent years, neural systems have demonstrated highly effective learning ability and superior perception intelligence. However, they have been found to lack effective reasoning and cognitive ability. On the other hand, symbolic systems exhibit exceptional cognitive intelligence but suffer from poor learning capabilities when compared to neural systems. Recognizing the advantages and disadvantages of both methodologies, an ideal solution emerges: combining neural systems and symbolic systems to create neural-symbolic learning systems that possess powerful perception and cognition. The purpose of this paper is to survey the advancements in neural-symbolic learning systems from four distinct perspectives: challenges, methods, applications, and future directions. By doing so, this research aims to propel this emerging field forward, offering researchers a comprehensive and holistic overview. This overview will not only highlight the current state-of-the-art but also identify promising avenues for future research.
References in corpus (19)
- Semi-Supervised Classification with Graph Convolutional Networks
- Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
- Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
- Harnessing Deep Neural Networks with Logic Rules
- Towards Deep Symbolic Reinforcement Learning
- Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge
- Probabilistic Logic Neural Networks for Reasoning
- Programming with a Differentiable Forth Interpreter
- Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples
- Neural Module Networks for Reasoning over Text
- Efficient Probabilistic Logic Reasoning with Graph Neural Networks
- TensorLog: Deep Learning Meets Probabilistic DBs
- Inductive Logic Programming via Differentiable Deep Neural Logic Networks
- Logical Rule Induction and Theory Learning Using Neural Theorem Proving
- Towards Symbolic Reinforcement Learning with Common Sense
- Recommendation Systems for Tourism Based on Social Networks: A Survey
- Neuro-Symbolic Constraint Programming for Structured Prediction
- Neural Markov Logic Networks
- Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings