Abstract
The necessity for neural-symbolic integration becomes evident as more complex problems like visual question answering are beginning to be addressed, which go beyond such limited-domain tasks as classification. Many existing state-of-the-art models are designed for a particular task or even benchmark, while general-purpose approaches are rarely applied to a wide variety of tasks demonstrating high performance. We propose a hybrid neural-symbolic framework, which tightly integrates the knowledge representation and symbolic reasoning mechanisms of the OpenCog cognitive architecture and one of the contemporary deep learning libraries, PyTorch, and show how to implement some existing particular models in our general framework.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Duch, W., Oentaryo, R.J., Pasquier, M.: Cognitive architectures: where do we go from here. In: Proceedings of 1st AGI Conference. Frontiers in Artificial Intelligence and Applications, vol. 171, pp. 122–136 (2008)
Besold, T.R., et al.: Neural-symbolic learning and reasoning: a survey and interpretation. arXiv preprint, arXiv:1711.03902 (2017)
Manhaeve, R.M., et al.: DeepProbLog: neural probabilistic logic programming. arXiv preprint, arXiv:1805.10872 (2018)
Overlan, M.C., Jacobs, R.A., Piantadosi, S.T.: Learning abstract visual concepts via probabilistic program induction in a Language of Thought. Cognition 168, 320–334 (2017)
Mascharka, D., Tran, Ph., Soklaski, R., Majumdar, A.: Transparency by design: closing the gap between performance and interpretability in visual reasoning. arXiv preprint, arXiv:1803.05268 (2018)
Fodor, J.A., Pylyshyn, Z.W.: Connectionism and cognitive architecture: a critical analysis. Cognition 28(1–2), 3–71 (1988)
Singh, J., Ying, V., Nutkiewicz, A.: Attention on attention: architectures for Visual Question Answering (VQA). arXiv preprint, arXiv:1803.07724 (2018)
Johnson, J.: Inferring and executing programs for visual reasoning. arXiv preprint, arXiv:1705.03633 (2017)
Agrawal, A., et al.: Don’t just assume; look and answer: overcoming priors for visual question answering. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 4971–4980 (2018)
Johnson, J., et al.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. arXiv preprint, arXiv:1612.06890 (2016)
Hudson, D.A., Manning, Ch.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. arXiv preprint, arXiv:1902.09506 (2019)
Goertzel, B.: Perception processing for general intelligence: bridging the symbolic/subsymbolic gap. In: Bach, J., Goertzel, B., Iklé, M. (eds.) AGI 2012. LNCS (LNAI), vol. 7716, pp. 79–88. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35506-6_9
Goertzel, B.: OpenCog NS: a deeply-interactive hybrid neural-symbolic cognitive architecture designed for global/local memory synergy. In: Proceedings of AAAI Fall Symposium Series FS-09-01, pp. 63–68 (2009)
Potapov, A., Zhdanov, I., Scherbakov, O., Skorobogatko, N., Latapie, H., Fenoglio, E.: Semantic image retrieval by uniting deep neural networks and cognitive architectures. In: Iklé, M., Franz, A., Rzepka, R., Goertzel, B. (eds.) AGI 2018. LNCS (LNAI), vol. 10999, pp. 196–206. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-97676-1_19
Yi, K., et al.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. arXiv preprint, arXiv:1810.02338 (2018)
Potapov, A., Belikov, A., Bogdanov, V., Scherbatiy, A.: Differentiable probabilistic logic networks. arXiv preprint, arXiv:1907.04592 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Potapov, A., Belikov, A., Bogdanov, V., Scherbatiy, A. (2019). Cognitive Module Networks for Grounded Reasoning. In: Hammer, P., Agrawal, P., Goertzel, B., Iklé, M. (eds) Artificial General Intelligence. AGI 2019. Lecture Notes in Computer Science(), vol 11654. Springer, Cham. https://doi.org/10.1007/978-3-030-27005-6_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-27005-6_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27004-9
Online ISBN: 978-3-030-27005-6
eBook Packages: Computer ScienceComputer Science (R0)