Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
arXiv:1711.03902
Abstract
The study and understanding of human behaviour is relevant to computer science, artificial intelligence, neural computation, cognitive science, philosophy, psychology, and several other areas. Presupposing cognition as basis of behaviour, among the most prominent tools in the modelling of behaviour are computational-logic systems, connectionist models of cognition, and models of uncertainty. Recent studies in cognitive science, artificial intelligence, and psychology have produced a number of cognitive models of reasoning, learning, and language that are underpinned by computation. In addition, efforts in computer science research have led to the development of cognitive computational systems integrating machine learning and automated reasoning. Such systems have shown promise in a range of applications, including computational biology, fault diagnosis, training and assessment in simulators, and software verification. This joint survey reviews the personal ideas and views of several researchers on neural-symbolic learning and reasoning. The article is organised in three parts: Firstly, we frame the scope and goals of neural-symbolic computation and have a look at the theoretical foundations. We then proceed to describe the realisations of neural-symbolic computation, systems, and applications. Finally we present the challenges facing the area and avenues for further research.
arXiv comment58 pages, work in progress
References in corpus (1)
Cited by in corpus (57)
- Deep Learning: A Critical Appraisal
- A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks
- Incorporating Domain Knowledge into Deep Neural Networks
- Onto2Vec: joint vector-based representation of biological entities and their ontology-based annotations
- Neural Collaborative Reasoning
- Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review
- Exploring the landscapes of "computing": digital, neuromorphic, unconventional -- and beyond
- Neurosymbolic Reinforcement Learning and Planning: A Survey
- Augmenting deep neural networks with symbolic knowledge: Towards trustworthy and interpretable AI for education
- Incorporating Symbolic Domain Knowledge into Graph Neural Networks
- Discrete and continuous representations and processing in deep learning: Looking forward
- Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge
- A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligence
- A Review of Emerging Research Directions in Abstract Visual Reasoning
- Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
- Logical Rule Induction and Theory Learning Using Neural Theorem Proving
- T-Norms Driven Loss Functions for Machine Learning
- Faster-LTN: a neuro-symbolic, end-to-end object detection architecture
- Recurrent Relational Networks
- ProTo: Program-Guided Transformer for Program-Guided Tasks
- Analyzing Differentiable Fuzzy Logic Operators
- Reasoning over RDF Knowledge Bases using Deep Learning
- Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning
- Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions
- Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices
- Differentiable Logic Machines
- Generalize Symbolic Knowledge With Neural Rule Engine
- DeepLogic: Towards End-to-End Differentiable Logical Reasoning
- A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making
- ToyArchitecture: Unsupervised Learning of Interpretable Models of the World
- Neural Markov Logic Networks
- From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
- Modeling Penetration Testing with Reinforcement Learning Using Capture-the-Flag Challenges: Trade-offs between Model-free Learning and A Priori Knowledge
- A Survey on Neural-symbolic Learning Systems
- Embedding Symbolic Knowledge into Deep Networks
- Collaboratively boosting data-driven deep learning and knowledge-guided ontological reasoning for semantic segmentation of remote sensing imagery
- Augmenting Neural Networks with First-order Logic
- Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes
- Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
- The relational processing limits of classic and contemporary neural network models of language processing
- NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
- Neurosymbolic AI for Situated Language Understanding
- EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case
- On the Capabilities of Pointer Networks for Deep Deductive Reasoning
- Neuro-Symbolic VQA: A review from the perspective of AGI desiderata
- Integrating Intrinsic and Extrinsic Explainability: The Relevance of Understanding Neural Networks for Human-Robot Interaction
- pix2rule: End-to-end Neuro-symbolic Rule Learning
- Completion Reasoning Emulation for the Description Logic EL+
- Toward Building Science Discovery Machines
- Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling
- Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning
- Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learning
- Neural Networks Enhancement with Logical Knowledge
- Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Neuro-Symbolic Algorithms
- Learning Invariants through Soft Unification
- Automated Fact-Checking: A Survey
- BF++: a language for general-purpose program synthesis