Abstract
Cognitive modeling and neuromorphic computing are two promising avenues to achieve AGI. However, neither of them has achieved intelligent agents with human-like proficiency so far. One possibility is that the two fields have developed in isolation at different levels, ignoring each other’s complementary features. In this paper, from a graph perspective, we present a framework that bridges the gap through cross-hierarchy structured representation and computation. Combining top-down and bottom-up design methodologies, coherent coordination of cognitive architecture and underlying neural dynamics is realized, where interpretable representation of entities and relations is constructed by hierarchical neuromorphic graph (HNG) via multi-scale projecting and abstraction. An assembly-based graph-oriented spiking message network is dedicatedly developed to conduct reasoning and learning. Evaluation on multi-modal reasoning benchmark indicates that the approach outperforms pure symbolic rule-based and non-neuromorphic baselines. Besides, the framework is flexible and compatible with the mainstream cognitive architectures meanwhile maintaining rich biological fidelity in order for exploiting non-negligible fine-grained mechanisms that are crucial for functionality emerging. Our methodology offers a brand-new guideline for the creation of more intelligent, adaptable, and autonomous systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Miller, G.A., Eugene, G., Pribram, K.H.: Plans and the structure of behaviour. In: Systems Research for Behavioral Sciencesystems Research, pp. 369–382. Routledge (2017)
Newell, A., Simon, H.A., et al.: Human Problem Solving, vol. 104. Prentice-hall Englewood Cliffs, NJ (1972)
Laird, J.E.: The Soar Cognitive Architecture. MIT press, Cambridge (2019)
Anderson, R.J.: The Architecture of Cognition, vol. 5. Psychology Press, London (1996)
O’reilly, R.C., Munakata, Y.: Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain. MIT press, Cambridge (2000)
Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)
Yamazaki, T., Tanaka, S.: The cerebellum as a liquid state machine. Neural Netw. 20(3), 290–297 (2007)
Jaeger, H.: Echo state network. Scholarpedia 2(9), 2330 (2007)
Mead, C., Ismail, M.: Analog VLSI implementation of neural systems, vol. 80. Springer, Berlin (1989)
Furber, S.B., et al.: Overview of the spinnaker system architecture. IEEE Trans. Comput. 62(12), 2454–2467 (2012)
Schmitt, S., et al.: Neuromorphic hardware in the loop: training a deep spiking network on the BrainScales wafer-scale system. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 2227–2234. IEEE (2017)
Merolla, P.A., et al.: A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345(6197), 668–673 (2014)
Ben Benjamin, V., et al.: Neurogrid: a mixed-analog-digital multichip system for large-scale neural simulations. Proc. IEEE 102(5), 699–716 (2014)
Pei, J., et al.: Towards artificial general intelligence with hybrid Tianjic chip architecture. Nature 572(7767), 106–111 (2019)
Zhao, R., et al.: A framework for the general design and computation of hybrid neural networks. Nat. Commun. 13(1), 3427 (2022)
Xu, M., Liu, F., Pei, J.: Endowing spiking neural networks with homeostatic adaptivity for APS-DVS bimodal scenarios. In: Companion Publication of the 2022 International Conference on Multimodal Interaction, pp. 12–17 (2022)
Zheng, H., Lin, H., Zhao, R., Shi, L.: Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention. arXiv preprint arXiv:2211.06027, 2022
Hao, Y., Huang, X., Dong, M., Bo, X.: A biologically plausible supervised learning method for spiking neural networks using the symmetric STDP rule. Neural Netw. 121, 387–395 (2020)
Kheradpisheh, S.R., Ganjtabesh, M., Thorpe, S.J., Masquelier, T.: STDP-based spiking deep convolutional neural networks for object recognition. Neural Netw. 99, 56–67 (2018)
Yujie, W., et al.: Brain-inspired global-local learning incorporated with neuromorphic computing. Nat. Commun. 13(1), 65 (2022)
Yang, Y., et al.: Bio-realistic and versatile artificial dendrites made of anti-ambipolar transistors. arXiv preprint arXiv:2212.01277 (2022)
Yang, Y., et al.: A mempolar transistor made from tellurium. arXiv preprint arXiv:2301.01986 (2023)
Wang, Y., et al.: Self-doping memristors with equivalently synaptic ion dynamics for neuromorphic computing. ACS Appl. Mater. Int. 11(27), 24230–24240 (2019)
Yang, Y., et al.: A new opportunity for the emerging tellurium semiconductor: making resistive switching devices. Nat. Commun. 12(1), 6081 (2021)
Marr, David: Vision: A Computational Investigation Into the Human Representation and Processing of Visual Information. MIT press, Cambridge (2010)
Canolty, R.T., Knight, R.T.: The functional role of cross-frequency coupling. Trends Cogn. Sci. 14(11), 506–515 (2010)
O’keefe, J., Nadel, L.: Précis of o’keefe & nadel’s the hippocampus as a cognitive map. Behav. Brain Sci. 2(4), 487–494 (1979)
Eliasmith, C., Anderson, C.H.: Neural Engineering: Computation, Representation, and Dynamics in Neurobiological Systems. MIT press, Cambridge (2003)
Laird, J.E.: An analysis and comparison of ACT-R and soar. arXiv preprint arXiv:2201.09305 (2022)
Laird, J.E., Lebiere, C., Rosenbloom, P.S.: A standard model of the mind: toward a common computational framework across artificial intelligence, cognitive science, neuroscience, and robotics. Ai Mag. 38(4), 13–26 (2017)
Xu, M., Wu, Y., Deng, L., Liu, F., Li, G., Pei, J.: Exploiting spiking dynamics with spatial-temporal feature normalization in graph learning. arXiv preprint arXiv:2107.06865 (2021)
Gu, F., Sng, W., Taunyazov, T., Soh, H.: TactileSGNET: a spiking graph neural network for event-based tactile object recognition. In: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 9876–9882. IEEE (2020)
Dold, D., Garrido, J.S., Chian, V.C., Hildebrandt, M., Runkler, T.: Neuro-symbolic computing with spiking neural networks. In: Proceedings of the International Conference on Neuromorphic Systems, vol. 2022, pp. 1–4 (2022)
Bellec, G., et al.: A solution to the learning dilemma for recurrent networks of spiking neurons. Nat. Commun. 11(1), 3625 (2020)
Papadimitriou, C.H., Vempala, S.S., Mitropolsky, D., Collins, M., Maass, W.: Brain computation by assemblies of neurons. Proc. Nat. Acad. Sci. 117(25), 14464–14472 (2020)
Acknowledgements
This work was supported by Science and Technology Innovation 2030 - New Generation of Artificial Intelligence, China project (2020AAA0109101), Zhejiang Lab’s International Talent Fund for Young Professionals, and National Natural Science Foundation of China (No. 62106119, 62276151). We thank Lukai Li for helpful discussions.
Author information
Authors and Affiliations
Corresponding authors
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
Xu, M., Zheng, H., Pei, J., Deng, L. (2023). A Unified Structured Framework for AGI: Bridging Cognition and Neuromorphic Computing. In: Hammer, P., Alirezaie, M., Strannegård, C. (eds) Artificial General Intelligence. AGI 2023. Lecture Notes in Computer Science(), vol 13921. Springer, Cham. https://doi.org/10.1007/978-3-031-33469-6_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-33469-6_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33468-9
Online ISBN: 978-3-031-33469-6
eBook Packages: Computer ScienceComputer Science (R0)