Abstract
The paper presents a “horizontal neuro-symbolic integration” approach for artificial general intelligence along with elementary representation-agnostic cognitive architecture and explores its usability under the experiential learning framework for reinforcement learning problem powered by “global feedback”.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tsamoura, E., Michael, L.: Neural-Symbolic Integration: A Compositional Perspective (2020). arXiv:2010.11926 [cs.AI]. https://arxiv.org/abs/2010.11926
Garcez, A., et al.: Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning (2019). arXiv:1905.06088 [cs.AI]
Silver, D., et al.: Reward is Enough. Artificial Intelligence, vol. 299 (October 2021). https://doi.org/10.1016/j.artint.2021.103535
Francois-Lavet, V., et al.: An Introduction to Deep Reinforcement Learning (2018). arXiv:1811.12560 [cs.LG]. https://arxiv.org/abs/1811.12560
Moreira, I., et al.: Deep Reinforcement Learning with Interactive Feedback in a Human-Robot Environment (2020). arXiv:2007.03363 [cs.AI]. https://arxiv.org/abs/2007.03363
Mnih, V., et al.: Playing Atari with Deep Reinforcement Learning (2013). arXiv:1312.5602 [cs.LG]. https://arxiv.org/abs/1312.5602
Kahneman, D.: Thinking, Fast and Slow. Farrar Straus & Giroux, January 1, 1994 (1994)
Marcus, G.: The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence (2020). arXiv:2002.06177 [cs.AI]. https://arxiv.org/abs/2002.06177v1
Mostafa, H., et al.: Deep Supervised Learning Using Local Errors (2017). arXiv:1711.06756 [cs.NE]. https://arxiv.org/abs/1711.06756
Lindsey, J., Ashok Litwin-Kumar, A.: Learning to Learn with Feedback and Local Plasticity (2020). arXiv:2006.09549 [cs.NE]. https://arxiv.org/abs/2006.09549
Ciszak, M., et al.: Emergent Excitability in Adaptive Networks of Non-Excitable Units (2020). arXiv:2010.06249 [nlin.AO]. https://arxiv.org/abs/2010.06249
Aljaberi, S., et al.: Global and Local Synaptic Regulation Determine the Stability of Homeostatic Plasticity (2021). arXiv:2103.15001 [nlin.AO]. https://arxiv.org/abs/2103.15001
Noh, K., et al.: Impaired coupling of local and global functional feedbacks underlies abnormal synchronization and negative symptoms of schizophrenia. BMC Syst. Biol. 7(1), 30 (2013). https://doi.org/10.1186/1752-0509-7-30
Kolb, A., Kolb, D.: Experiential learning theory. In: Encyclopedia of the Sciences of Learning, pp. 1212−1219. Springer, Boston (2012). https://doi.org/10.1007/978-1-4419-1428-6_227
Zbontar, J., et al.: Barlow Twins: Self-Supervised Learning via Redundancy Reduction (2021). arXiv:2103.03230 [cs.CV]. https://arxiv.org/abs/2103.03230
Arrieta, A.B., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82–115 (2019). https://doi.org/10.1016/j.inffus.2019.12.012
Rudin, C., et al.: Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021). arXiv:2103.11251 [cs.LG]. https://arxiv.org/abs/2103.11251
Vityaev, E.: Semantic Probabilistic Inference of Predictions. In: Series «Mathematics», vol. 21 (2017). https://doi.org/10.26516/1997-7670.2017.21.33
Kolonin, A.: Controlled Language and Baby Turing Test for General Conversational Intelligence (2020). arXiv:2005.09280 [cs.AI]. https://arxiv.org/abs/2005.09280
Vityaev, E.E., Demin, A.V., Kolonin, Y.A.: Logical probabilistic biologically inspired cognitive architecture. In: Goertzel, B., Panov, A.I., Potapov, A., Yampolskiy, R. (eds.) AGI 2020. LNCS (LNAI), vol. 12177, pp. 337–346. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-52152-3_36
Kolonin, A.: Computable cognitive model based on social evidence and restricted by resources: applications for personalized search and social media in multi-agent environments. In: 2015 International Conference on Biomedical Engineering and Computational Technologies (2015). https://ieeexplore.ieee.org/document/7361869?arnumber=7361869
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Kolonin, A. (2022). Neuro-Symbolic Architecture for Experiential Learning in Discrete and Functional Environments. In: Goertzel, B., Iklé, M., Potapov, A. (eds) Artificial General Intelligence. AGI 2021. Lecture Notes in Computer Science(), vol 13154. Springer, Cham. https://doi.org/10.1007/978-3-030-93758-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-93758-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93757-7
Online ISBN: 978-3-030-93758-4
eBook Packages: Computer ScienceComputer Science (R0)