Abstract
While end-to-end learning systems are rapidly gaining capabilities and popularity, the increasing computational demands for deploying such systems, along with a lack of flexibility, adaptability, explainability, reasoning and verification capabilities, require new types of architectures. Here we introduce a classification of hybrid systems which, based on an analysis of human knowledge and intelligence, combines neural learning with various types of knowledge and knowledge sources. We present the Thrill-K architecture as a prototypical solution for integrating instantaneous knowledge, standby knowledge and external knowledge sources in a framework capable of inference, learning and intelligent control.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2018). arXiv preprint. arXiv:1810.04805
Amodei, D.: AI and Compute. OpenAI (2021). https://openai.com/blog/ai-and-compute/
Interpreting AI compute trends. AI Impacts (2020). https://aiimpacts.org/interpreting-ai-compute-trends/
Kahneman, D.: Thinking, Fast and Slow. Macmillan, New York (2011)
Bengio, Y.: From system 1 deep learning to system 2 deep learning. In Neural Information Processing Systems (2019)
Chollet, F.: On the measure of intelligence (2019). arXiv preprint arXiv:1911.01547
Launchbury, J.: A DARPA perspective on artificial intelligence (2017). Accessed 11 Nov 2019
Goyal, A., Bengio, Y.: Inductive biases for deep learning of higher-level cognition (2020). arXiv preprint. arXiv:2011.15091
Kautz, H.: The third AI summer: AAAI Robert S engelmore memorial lecture. AI Mag. 43(1), 93–104 (2022)
Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9459-9474 (2020)
Chakraborty, N., Lukovnikov, D., Maheshwari, G., Trivedi, P., Lehmann, J., Fischer, A.: Introduction to neural network based approaches for question answering over knowledge graphs (2019). arXiv preprint. arXiv:1907.09361
Kapanipathi, P., et al.: Leveraging abstract meaning representation for knowledge base question answering (2020). arXiv preprint. arXiv:2012.01707
Singhal, A.: Introducing the knowledge graph: things, not strings. Official Google Blog 5, 16 (2012)
Thompson, N.C., Greenewald, K., Lee, K., Manso, G.F.: The computational limits of deep learning (2020) (2020). arXiv preprint. arXiv:2007.05558
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Singer, G. et al. (2023). Thrill-K Architecture: Towards a Solution to the Problem of Knowledge Based Understanding. In: Goertzel, B., Iklé, M., Potapov, A., Ponomaryov, D. (eds) Artificial General Intelligence. AGI 2022. Lecture Notes in Computer Science(), vol 13539. Springer, Cham. https://doi.org/10.1007/978-3-031-19907-3_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-19907-3_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19906-6
Online ISBN: 978-3-031-19907-3
eBook Packages: Computer ScienceComputer Science (R0)