Abstract
The hippocampus is the brain area used for localisation, mapping and episodic memory. Humans and animals can outperform robotic systems in these tasks, so functional models of hippocampus may be useful to improve robotic navigation, such as for self-driving cars. Previous work developed a biologically plausible model of hippocampus based on Unitary Coherent Particle Filter (UCPF) and Temporal Restricted Boltzmann Machine, which was able to learn to navigate around small test environments. However it was implemented in serial software, which becomes very slow as the environments and numbers of neurons scale up. Modern GPUs can parallelize execution of neural networks. The present Neural Software Engineering study develops a GPU accelerated version of the UCPF hippocampus software, using the formal Software Engineering techniques of profiling, optimisation and test-driven refactoring. Results show that the model can greatly benefit from parallel execution, which may enable it to scale from toy environments and applications to real-world ones such as self-driving car navigation. The refactored parallel code is released to the community as open source software as part of this publication.
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
Notes
- 1.
The ‘wake-sleep’ algorithm is a machine learning structure which is here unrelated to night time sleep behaviour of the hippocampus. Night time slow wave sleep is thought to be involved in consolidating memories from hippocampus to cortex so is outside the scope of the UCPF model.
- 2.
Sigmoid functions were found to be a bottleneck in pure machine learning DNNs, where they are now replaced by rectified linear units (ReLUs) for speed. However sigmoids are required in UCPF for biological plausibility, and our aim in refactoring is to preserve neural functionality rather than make such approximations.
References
Abadi, M.: Tensorflow: learning functions at scale. In: Proceedings of the 21st ACM SIGPLAN International Conference on Functional Programming, pp. 1–1 (2016)
Andersen, P., Morris, R., Amaral, D., Bliss, T., O’Keefe, J.: The Hippocampus Book. Oxford University Press, London (2006)
Bengio, Y., Goodfellow, I., Courville, A.: Deep Learning, vol. 1. MIT Press, Cambridge (2017)
Boss, B.D., Turlejski, K., Stanfield, B.B., Cowan, W.M.: On the numbers of neurons on fields ca1 and ca3 of the hippocampus of sprague-dawley and wistar rats. Brain Res. 406(1–2), 280–287 (1987)
Fowler, M.: Refactoring: Improving the Design of Existing Code. Addison-Wesley Professional, Boston (2018)
Fox, C., Prescott, T.: Hippocampus as unitary coherent particle filter. In: The 2010 International Joint Conference on. Neural Networks (IJCNN), pp. 1–8 (2010)
Fox, C., Prescott, T.: Learning in a unitary coherent hippocampus. In: Artificial Neural Networks (ICANN) (2010)
Harding, A., Halliday, G., Kril, J.: Variation in hippocampal neuron number with age and brain volume. Cerebral Cortex (New York, NY: 1991) 8(8), 710–718 (1998)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Owens, J.: GPU architecture overview. In: ACM SIGGRAPH 2007 Courses, pp. 2-es (2007)
Saul, A., Prescott, T., Fox, C.: Scaling up a boltzmann machine model of hippocampus with visual features for mobile robots. In: 2011 IEEE International Conference on Robotics and Biomimetics, pp. 835–840 (2011)
Sutskever, I., Hinton, G.E., Taylor, G.W.: The recurrent temporal restricted boltzmann machine. In: 21st Proceedings of the International Conference on Advances in Neural Information Processing Systems (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Stevenson, J., Fox, C. (2022). Scaling a Hippocampus Model with GPU Parallelisation and Test-Driven Refactoring. In: Hunt, A., et al. Biomimetic and Biohybrid Systems. Living Machines 2022. Lecture Notes in Computer Science(), vol 13548. Springer, Cham. https://doi.org/10.1007/978-3-031-20470-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-20470-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20469-2
Online ISBN: 978-3-031-20470-8
eBook Packages: Computer ScienceComputer Science (R0)