Humans are often extraordinary at performing practical reasoning. There are cases where the human computer, slow as it is, is faster than any artificial intelligence system. Are we faster because of the way we perceive knowledge as opposed to the way we represent it? The authors address this question by presenting neural network models that integrate the two most fundamental phenomena of cognition: our ability to learn from experience, and our ability to reason from what has been learned. This book is the first to offer a self-contained presentation of neural network models for a number of computer science logics, including modal, temporal, and epistemic logics. By using a graphical presentation, it explains neural networks through a sound neural-symbolic integration methodology, and it focuses on the benefits of integrating effective robust learning with expressive reasoning capabilities. The bookwill be invaluable reading for academic researchers, graduate students, and senior undergraduates in computer science, artificial intelligence, machine learning, cognitive science and engineering. It will also be of interest to computational logicians, and professional specialists on applications of cognitive, hybrid and artificial intelligence systems.
Cited By
- Dickens C, Gao C, Pryor C, Wright S and Getoor L Convex and bilevel optimization for neural-symbolic inference and learning Proceedings of the 41st International Conference on Machine Learning, (10865-10896)
- Pryor C, Dickens C, Augustine E, Albalak A, Wang W and Getoor L NeuPSL Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, (4145-4153)
- Li Q, Siyuan Huang S, Hong Y, Chen Y, Wu Y and Zhu S Closed loop neural-symbolic learning via integrating neural perception, grammar parsing, and symbolic reasoning Proceedings of the 37th International Conference on Machine Learning, (5884-5894)
- Caccavale R and Finzi A (2019). Learning attentional regulations for structured tasks execution in robotic cognitive control, Autonomous Robots, 43:8, (2229-2243), Online publication date: 1-Dec-2019.
- Guo X, Zhang H, Ye L, Li S and Pokrajac D (2019). RnRTD, Computational Intelligence and Neuroscience, 2019, Online publication date: 1-Jan-2019.
- Saldanha E, Hölldobler S, Ramli C and Medinacelli L (2019). A core method for the weak completion semantics with skeptical abduction, Journal of Artificial Intelligence Research, 63:1, (51-86), Online publication date: 1-Sep-2018.
- Serafini L, Donadello I and Garcez A Learning and reasoning in logic tensor networks Proceedings of the Symposium on Applied Computing, (125-130)
- Besold T, Garcez A, Stenning K, Torre L and Lambalgen M (2017). Reasoning in Non-probabilistic Uncertainty, Minds and Machines, 27:1, (37-77), Online publication date: 1-Mar-2017.
- Alashkar T, Jiang S, Wang S and Fu Y Examples-rules guided deep neural network for makeup recommendation Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, (941-947)
- Hatzilygeroudis I and Prentzas J (2015). Symbolic-neural rule based reasoning and explanation, Expert Systems with Applications: An International Journal, 42:9, (4595-4609), Online publication date: 1-Jun-2015.
- Riveret R, Pitt J, Korkinof D and Draief M Neuro-Symbolic Agents Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, (1481-1489)
- Dorn M, e Silva M, Buriol L and Lamb L (2014). Three-dimensional protein structure prediction, Computational Biology and Chemistry, 53:PB, (251-276), Online publication date: 1-Dec-2014.
- de Penning L, d'Avila Garcez A, Lamb L and Meyer J Neural-symbolic cognitive agents Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems, (1621-1622)
- Pinkas G, Lima P and Cohen S A dynamic binding mechanism for retrieving and unifying complex predicate-logic knowledge Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I, (482-490)
- Borges R, d'Avila Garcez A, Lamb L and Nuseibeh B Learning to adapt requirements specifications of evolving systems (NIER track) Proceedings of the 33rd International Conference on Software Engineering, (856-859)
- Borges R, d'Avila Garcez A and Lamb L Integrating model verification and self-adaptation Proceedings of the 25th IEEE/ACM International Conference on Automated Software Engineering, (317-320)
- Komendantskaya E, Broda K and Garcez A Neuro-symbolic representation of logic programs defining infinite sets Proceedings of the 20th international conference on Artificial neural networks: Part I, (301-304)
Index Terms
- Neural-Symbolic Cognitive Reasoning
Recommendations
Towards the Synergy of Cognitive Informatics, Neural Informatics, Brain Informatics, and Cognitive Computing
The contemporary wonder of sciences and engineering recently refocused on the starting point: how the brain processes internal and external information autonomously rather than imperatively as those of conventional computers? This paper explores the ...
Neural-Symbolic Methods for Knowledge Graph Reasoning: A Survey
Neural symbolic knowledge graph (KG) reasoning offers a promising approach that combines the expressive power of symbolic reasoning with the learning capabilities inherent in neural networks. This survey provides a comprehensive overview of advancements, ...