Abstract
Neurons in the medial superior temporal (MSTd) region of the visual cortex of the brain can efficiently recognize the firing patterns from the neurons in the MT region. The process is similar to sparse coding in non-negative matrix decomposition (NMF), and the modular recognition of images can be achieved through synaptic plasticity learning rules. In this paper, a spiking neural network model based on spike-timing-dependent plasticity (STDP) is built to simulate the processing process of the visual cortex region MT-MSTD. Our results show that STDP can perform similar functions as NMF, i.e. generating sparse and linear superimposed output based on local features, so as to accurately reconstruct input stimuli for image reconstruction. Finally, support vector machine is used to achieve image recognition of optical flow inputs in eight directions. Compared with NMF, local feature extraction using STDP does not need to retrain the decision layer during the testing procedure of new optical flow samples, contributing to more efficient recognition of optical flow images.
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
References
Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381(6583), 607–609 (1996). https://doi.org/10.1038/381607a0
Jin, Y., Zhang, W., Li, P.: Hybrid macro/micro level backpropagation for training deep spiking neural networks. In: Advances in Neural Information Processing Systems, vol. 31 (2018). https://doi.org/10.48550/arXiv.1805.07866
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). https://doi.org/10.1016/j.neunet.2017.12.005
Li, J., Hu, W., Yuan, Y., Huo, H., Fang, T.: Bio-inspired deep spiking neural network for image classification. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds.) Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, 14–18 November 2017, Proceedings, Part II 24. pp. 294–304. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-70096-0_31
Graziano, M., Andersen, R.A., Snowden, R.J.: Tuning of MST neurons to spiral motions. J. Neurosci. 14(1), 54–67 (1994). https://doi.org/10.1523/JNEUROSCI.14-01-00054.1994
Logan, D.J., Duffy, C.J.: Cortical area MSTD combines visual cues to represent 3-d self-movement. Cerebral Cortex 16(10), 1494–1507 (2006). https://doi.org/10.1093/cercor/bhj082
Beyeler, M., Dutt, N., Krichmar, J.L.: 3d visual response properties of MSTD emerge from an efficient, sparse population code. J. Neurosci. 36(32), 8399–8415 (2016). https://doi.org/10.1523/JNEUROSCI.0396-16.2016
Chen, K., Beyeler, M., Krichmar, J.L.: Cortical motion perception emerges from dimensionality reduction with evolved spike-timing-dependent plasticity rules. J. Neurosci. 42(30), 5882–5898 (2022). https://doi.org/10.1523/JNEUROSCI.0384-22.2022
Beyeler, M., Rounds, E.L., Carlson, K.D., Dutt, N., Krichmar, J.L.: Neural correlates of sparse coding and dimensionality reduction. PLoS Comput. Biol. 15(6), e1006908 (2019). https://doi.org/10.1371/journal.pcbi.1006908
Longuet-Higgins, H.C., Prazdny, K.: The interpretation of a moving retinal image. Proc. R. Soc. London. Ser. B. Biol. Sci. 208(1173), 385–397 (1980). https://doi.org/10.1098/rspb.1980.0057
Britten, K.H., van Wezel, R.J.: Electrical microstimulation of cortical area MST biases heading perception in monkeys. Nat. Neurosci. 1(1), 59–63 (1998). https://doi.org/10.1038/259
Nover, H., Anderson, C.H., DeAngelis, G.C.: A logarithmic, scale-invariant representation of speed in macaque middle temporal area accounts for speed discrimination performance. J. Neurosci. 25(43), 10049–10060 (2005). https://doi.org/10.1523/JNEUROSCI.1661-05.2005
Bidaut, G., Ochs, M.F.: Clutrfree: cluster tree visualization and interpretation. Bioinformatics 20(16), 2869–2871 (2004). https://doi.org/10.1093/bioinformatics/bth307
Wang, G., Kossenkov, A.V., Ochs, M.F.: Ls-NMF: a modified non-negative matrix factorization algorithm utilizing uncertainty estimates. BMC Bioinf. 7(1), 1–10 (2006). https://doi.org/10.1186/1471-2105-7-175
Luke, S.: Ecj then and now. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 1223–1230 (2017). https://doi.org/10.1145/3067695.3082467
Tang, Z., Zhang, X., Zhang, S.: Robust perceptual image hashing based on ring partition and NMF. IEEE Trans. Knowl. Data Eng. 26(3), 711–724 (2013). https://doi.org/10.1109/TKDE.2013.45
Niedermeier, L., et al.: Carlsim 6: an open source library for large-scale, biologically detailed spiking neural network simulation. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1–10. IEEE (2022). https://doi.org/10.1109/IJCNN55064.2022.9892644
Carlson, K.D., Richert, M., Dutt, N., Krichmar, J.L.: Biologically plausible models of homeostasis and STDP: stability and learning in spiking neural networks. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2013). https://doi.org/10.1109/IJCNN.2013.6706961
Carlson, K.D., Nageswaran, J.M., Dutt, N., Krichmar, J.L.: An efficient automated parameter tuning framework for spiking neural networks. Front. Neurosci. 8, 10 (2014). https://doi.org/10.3389/fnins.2014.00010
Chang, C.C., Lin, C.J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 1–27 (2011). https://doi.org/10.1145/1961189.1961199
Ackonwledgments
This paper is supported by STI 2030-Major Project 2021ZD0201300. The authors would like to give sincere appreciations to Prof. Jeffrey Krichmar and Dr. Kexin Chen for their insightful suggestions and discussions for this work.
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 Singapore Pte Ltd.
About this paper
Cite this paper
Lin, W., Yi, H., Li, X. (2023). Image Reconstruction and Recognition of Optical Flow Based on Local Feature Extraction Mechanism of Visual Cortex. In: Zhang, H., et al. International Conference on Neural Computing for Advanced Applications. NCAA 2023. Communications in Computer and Information Science, vol 1869. Springer, Singapore. https://doi.org/10.1007/978-981-99-5844-3_2
Download citation
DOI: https://doi.org/10.1007/978-981-99-5844-3_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-5843-6
Online ISBN: 978-981-99-5844-3
eBook Packages: Computer ScienceComputer Science (R0)