Abstract
One goal of general intelligence is to learn novel information without overwriting prior learning, i.e. catastrophic forgetting (CF). The utility of preserving knowledge across training tasks is twofold: first, the system can return to previously learned tasks after learning something new. In addition, bootstrapping previous knowledge may allow for faster learning of a novel task. Current approaches to learning without forgetting depend on strategically preserving weights that are critical to a previously learned task. However, another potential factor that has been largely overlooked is leveraging the initial network topology, or architecture. Here, we propose that the topology of biological brains likely evolved certain features that are designed to achieve knowledge preservation. In particular, we consider that the highly conserved property of anatomical modularity may offer a solution to weight-update learning methods that leverages learning without catastrophic forgetting for general bootstrapping to novel circumstances. Final considerations are made on how to combine these two objectives in a general learning system.
Supported by Machine Perception and Cognitive Robotics Labs.
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
Aich, A.: Elastic weight consolidation (EWC): Nuts and bolts. arXiv preprint arXiv:2105.04093 (2021)
Bruce, L.L.: Evolution of the brain in reptiles. In: Binder, M.D., Hirokawa, N., Windhorst, U. (eds.) Encyclopedia of Neuroscience, pp. 1295–1301. Springer, Berlin (2009). https://doi.org/10.1007/978-3-540-29678-2_3147
Coward, L.A.: The recommendation architecture: lessons from large-scale electronic systems applied to cognition. Cogn. Syst. Res. 2(2), 111–156 (2001)
Coward, L.A.: A System Architecture Approach to the Brain: From Neurons to Consciousness. Nova Publishers, Hauppauge (2005)
Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: a survey. J. Mach. Learn. Res. 20(1), 1997–2017 (2019)
Gershenson, C.: Introduction to random Boolean networks. arXiv preprint nlin/0408006 (2004)
Goertzel, B., Pennachin, C.: Artificial General Intelligence. Springer, Berlin (2007). https://doi.org/10.1007/978-3-540-68677-4
Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139–144 (2020)
Goudarzi, A., Teuscher, C., Gulbahce, N., Rohlf, T.: Emergent criticality through adaptive information processing in Boolean networks. Phys. Rev. Lett. 108(12), 128702 (2012)
Goyal, A., Bengio, Y.: Inductive biases for deep learning of higher-level cognition. arXiv preprint arXiv:2011.15091 (2020)
Goyal, A., et al.: Recurrent independent mechanisms. arXiv preprint arXiv:1909.10893 (2019)
Gutowitz, H.: Cellular Automata: Theory and Experiment. MIT Press, Cambridge (1991)
György Buzsáki, M.: The Brain from Inside Out. Oxford University Press, Oxford (2019)
Hebb, D.O.: The Organisation of Behaviour: A Neuropsychological Theory. Science Editions, New York (1949)
Hutter, M.: A gentle introduction to the universal algorithmic agent AIXI (2003)
Ito, K., et al.: A systematic nomenclature for the insect brain. Neuron 81(4), 755–765 (2014)
Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Nat. Acad. Sci. 114(13), 3521–3526 (2017)
Kotrschal, A., Kotrschal, K.: Fish brains: anatomy, functionality, and evolutionary relationships. In: Kristiansen, T.S., Fernö, A., Pavlidis, M.A., van de Vis, H. (eds.) The Welfare of Fish. AW, vol. 20, pp. 129–148. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-41675-1_6
Koutník, J., Cuccu, G., Schmidhuber, J., Gomez, F.: Evolving large-scale neural networks for vision-based reinforcement learning. In: Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation, pp. 1061–1068 (2013)
Lalo, E., et al.: Patterns of bidirectional communication between cortex and basal ganglia during movement in patients with Parkinson disease. J. Neurosci. 28(12), 3008–3016 (2008)
Larsell, O.: The cerebellum of reptiles: lizards and snake. J. Comp. Neurol. 41(1), 59–94 (1926)
Lee, D.S.: Evolution of regulatory networks towards adaptability and stability in a changing environment. Phys. Rev. E 90(5), 052822 (2014)
Lukoševičius, M., Jaeger, H., Schrauwen, B.: Reservoir computing trends. KI-Künstliche Intell. 26(4), 365–371 (2012). https://doi.org/10.1007/s13218-012-0204-5
Werle van der Merwe, A.: Investigating the evolution of modularity in neural networks. Ph.D. thesis. Stellenbosch University, Stellenbosch (2020)
Nixon, J., Lakshminarayanan, B., Tran, D.: Why are bootstrapped deep ensembles not better? In: “I Can’t Believe It’s Not Better!” NeurIPS 2020 Workshop (2020)
Nomura, T., Izawa, E.I.: Avian brains: insights from development, behaviors and evolution. Dev. Growth Differ. 59(4), 244–257 (2017)
Ring, H., Serra-Mestres, J.: Neuropsychiatry of the basal ganglia. J. Neurol. Neurosurg. Psychiatry 72(1), 12–21 (2002)
Rosa, M., et al.: Badger: Learning to (learn [learning algorithms] through multi-agent communication). arXiv preprint arXiv:1912.01513 (2019)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Schölkopf, B., et al.: Toward causal representation learning. Proc. IEEE 109(5), 612–634 (2021)
Silver, D., Singh, S., Precup, D., Sutton, R.S.: Reward is enough. Artif. Intell. 299, 103535 (2021)
Stanley, K.O., Clune, J., Lehman, J., Miikkulainen, R.: Designing neural networks through neuroevolution. Nat. Mach. Intell. 1(1), 24–35 (2019)
Sutherland, R., Whishaw, I., Kolb, B.: Contributions of cingulate cortex to two forms of spatial learning and memory. J. Neurosci. 8(6), 1863–1872 (1988)
Tong, M.H., Joyce, C.A., Cottrell, G.W.: Why is the fusiform face area recruited for novel categories of expertise? a neurocomputational investigation. Brain Res. 1202, 14–24 (2008)
Trestman, M.: The Cambrian explosion and the origins of embodied cognition. Biol. Theory 8(1), 80–92 (2013). https://doi.org/10.1007/s13752-013-0102-6
Turing, A.: Intelligent machinery, 1948. In: The Essential Turing, p. 395 (1969)
Turing, A.M.: Computing machinery and intelligence. In: Epstein, R., Roberts, G., Beber, G. (eds.) Parsing the Turing Test, pp. 23–65. Springer, Dordrecht (2009). https://doi.org/10.1007/978-1-4020-6710-5_3
Vanschoren, J.: Meta-learning: A survey. arXiv preprint arXiv:1810.03548 (2018)
Wang, J., Elfwing, S., Uchibe, E.: Modular deep reinforcement learning from reward and punishment for robot navigation. Neural Netw. 135, 115–126 (2021)
Wang, R., Lehman, J., Clune, J., Stanley, K.O.: Paired open-ended trailblazer (POET): Endlessly generating increasingly complex and diverse learning environments and their solutions. arXiv preprint arXiv:1901.01753 (2019)
Weiss, K., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. J. Big data 3(1), 1–40 (2016)
Williams, S., Yaeger, L.: Evolution of neural dynamics in an ecological model. Geosciences 7(3), 49 (2017)
Xie, Z., He, F., Fu, S., Sato, I., Tao, D., Sugiyama, M.: Artificial neural variability for deep learning: on overfitting, noise memorization, and catastrophic forgetting. Neural Comput. 33(8), 1–30 (2020)
Yopak, K.E., Lisney, T.J., Darlington, R.B., Collin, S.P., Montgomery, J.C., Finlay, B.L.: A conserved pattern of brain scaling from sharks to primates. Proc. Nat. Acad. Sci. 107(29), 12946–12951 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
StClair, R.A., Edward Hahn, W., Barenholtz, E. (2022). The Role of Bio-Inspired Modularity in General Learning. 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_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-93758-4_27
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)