Dimensions of Neural-symbolic Integration - A Structured Survey

By Sebastian Bader, Pascal Hitzler. 2005

157 citations recorded by the source corpus.

Research on integrated neural-symbolic systems has made significant progress in the recent past. In particular the understanding of ways to deal with symbolic knowledge within connectionist systems (also called artificial neural networks) has reached a critical mass which enables the community to strive for applicable implementations and use cases. Recent work has covered a great variety of logics used in artificial intelligence and provides a multitude of techniques for dealing with them within the context of artificial neural networks. Already in the pioneering days of computational models of neural cognition, the question was raised how symbolic knowledge can be represented and dealt with within neural networks. The landmark paper [McCulloch and Pitts, 1943] provides fundamental insights how propositional logic can be processed using simple artificial neural networks. Within the following decades, however, the topic did not receive much attention as research in artificial intelligence initially focused on purely symbolic approaches. The power of machine learning using artificial neural networking was not recognized until the 80s, when in particular the backpropagation algorithm [Rumelhart et al., 1986] made connectionist learning feasible and applicable in practice. These advances indicated a breakthrough in machine learning which quickly led to industrial-strength applications in areas such as image analysis, speech and pattern recognition, investment analysis, engine monitoring, fault diagnosis, etc. During a training process from raw data, artificial neural networks acquire expert knowledge about the problem domain, and the ability to generalize this knowledge to similar but previously unencountered situations in a way which often surpasses the abilities of human experts. The knowledge obtained during the training process, however, is hidden within

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019, methodology): “Neural-symbolic computing aims at integrating, as put forward by Valiant, two most fundamental cognitive abilities: the ability to learn from experience, and the ability to reason from what has been learned [2, 12, 16].”
On the Binding Problem in Artificial Neural Networks (2020, background): “(2017) appear to argue for separating neural and symbolic information content, somewhat akin to hybrid approaches (Bader and Hitzler, 2005).”
Explaining Trained Neural Networks with Semantic Web Technologies: First Steps (2017, background): “This topic of explaining trained neural networks is not a new one, in fact there is already quite a bit of tradition and literature on the topic of rule extraction from such networks (see, e.g., [2,9,16]), which pursued very similar goals.”
Lifted Relational Neural Networks: Efficient Learning of Latent Relational Structures (2018, methodology): “There have been a few other approaches which adapt neural networks for relational learning (Franca, Zaverucha, & Garcez, 2014; Botta, A, & Piola, 1997; Bader & Hitzler, 2005; Ramon & De Raedt, 2000; Uwents, Monfardini, Blockeel, Gori, & Scarselli, 2011).”
Large Language Models (2023, background): “Given this point of view one can seek a synthesis or “neurosymbolic” approach, advocated in many works [7, 47, 72].”
Neural-Symbolic Learning and Reasoning: A Survey and Interpretation (2017, result): “…the research in the area of neural-symbolic integration for more than two decades now as evidenced by, for instance, the results summarised in the overview by (Bader & Hitzler, 2005), collected in the books by (Hammer & Hitzler, 2007) and (Garcez et al., 2009), and reported in the present survey.”
Explainable AI (XAI): Core Ideas, Techniques, and Solutions (2022, background): “High-level view of a neural-symbolic system [3].”
Neurosymbolic AI: the 3rd wave (2020, unknown): “Neural-symbolic computing has been an active area of research seeking to establish such a bridge for several years [4, 26, 16, 20, 35, 43, 80, 93].”