Abstract
Complex biological neural network is the result of long term evolution. The changes in the external environment will prompt the neural network to change its own structure. In this work, we try to build a bionic method to form self-growing and self-organizing neural networks. We have presented method for connection growing, verification and optimization. Paralleled way to simulate this process has also been presented in this work, using CPU \(+\) GPU style. We built a simulation platform to verify and test our methods. We conducted a series of experiments, to verify our method, and also to testify the ability of our algorithm. Results show that our method could generate neural network that could be helpful in detecting moving target.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abbott LF (1999) Lapicques introduction of the integrate-and-fire model neuron (1907). Brain Res Bull 50(5–6):303–304
Barabasi AL, Albert R (1999) Emergence of scaling in random networks. Science 286(5439):509–512
Egmont-Petersen M, Ridder DD, Handels H (2002) Image processing with neural networks: a review. Pattern Recognit 35(10):2279–2301
Fiesler E (1994) Comparative bibliography of ontogenic neural networks. Springer, London
Hebb DO (1949) The organization of behavior: a neuropsychological approach. J Am Med Assoc 143(1):74–76
Izhikevich EM (2004) Which model to use for cortical spiking neurons? IEEE Trans Neural Netw 15(5):1063–1070
Kasabov N (1998) Ecos: a framework for evolving connectionist systems and the eco learning paradigm. In: Proceedings of of Iconip98 Kitakyushu
Kasabov NK (2003) Evolving connectionist systems: methods and applications in bioinformatics, brain study and intelligent machines. Neural Netw IEEE Trans 16(1):286–286
Kasabov N, Dhoble K, Nuntalid N, Indiveri G (2012) Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition. Neural Netw Off J Int Neural Netw Soc 41(5):188–201
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Lichtsteiner P, Delbruck T (2005) A 64 x 64 aer logarithmic temporal derivative silicon retina. In: Research in microelectronics and electronics, pp. 202–205
Naveros F, Luque NR, Garrido JA, Carrillo RR, Anguita M, Ros E (2015) A spiking neural simulator integrating event-driven and time-driven computation schemes using parallel cpu-gpu co-processing: a case study. IEEE Trans Neural Netw Learn Syst 26(7):1567–1574
Orlowska-Kowalska T, Kaminski M (2011) Fpga implementation of the multilayer neural network for the speed estimation of the two-mass drive system. IEEE Trans Ind Inform 7(3):436–445
Prez Uribe A (1999) Structure-adaptable digital neural networks. Epfl
Quinlan PT (1998) Structural change and development in real and artificial neural networks. Neural Netw Off J Int Neural Netw Soc 11(4):577–599
Rowley HA, Baluja S, Kanade T (1996) Neural network-based face detection. IEEE Trans Pattern Anal Mach Intell 20(1):203–208
Schliebs S, Defoin-Platel M, Kasabov N (2008) Integrated feature and parameter optimization for an evolving spiking neural network. In: International conference on advances in neuro-information processing, pp 623–632
Schmidhuber J (2014) Deep learning in neural networks: an overview. Neural Netw 61:85–117
Shayani H, Bentley PJ, Tyrrell AM (2008) Hardware implementation of a bio-plausible neuron model for evolution and growth of spiking neural networks on FPGA. In: NASA/ESA conference on adaptive hardware and systems, AHS ’08, pp 236–243
Śmieja FJ (1993) Neural network constructive algorithms: trading generalization for learning efficiency? Circ Syst Signal Process 12(2):331–374
Soltic S, Wysoski SG, Kasabov NK (2008) Evolving spiking neural networks for taste recognition. Neural Netw 24(5):2091–2097
Watts M, Kasabov N (2000) Simple evolving connectionist systems and experiments on isolated phoneme recognition. In: IEEE symposium on combinations of evolutionary computation and neural networks, pp 232–239
Wysoski SG, Benuskova L, Kasabov N (2006a) Adaptive learning procedure for a network of spiking neurons and visual pattern recognition. In: International conference on advanced concepts for intelligent vision systems, pp 1133–1142
Wysoski SG, Benuskova L, Kasabov N (2006b) On-line learning with structural adaptation in a network of spiking neurons for visual pattern recognition. In: International conference on artificial neural networks—ICANN 2006, Athens, Greece, September 10–14, pp 61–70
Wysoski SG (2008) Evolving spiking neural networks for adaptive audiovisual pattern recognition. Auckland University of Technology, Auckland
Zaknich A (1998) Introduction to the modified probabilistic neural network for general signal processing applications. IEEE Trans Signal Process 46(7):1980–1990
Zhu X, Yuan L, Wang D, Chen Y (2010) FPGA implementation of a probabilistic neural network for spike sorting. In: Information engineering and computer science, pp 1–4
Acknowledgements
This work is supported by the National Natural Science Foundation of China under Grant No. 61502032, the Science and Technology Plan of Beijing Municipality under Grant No. Z161100000216147, the Core Electronic Devices, High-End General Purpose Processor, and Fundamental System Software of China under Grant No. 2012ZX01034-001-002, Tsinghua National Laboratory for Information Science and Technology (TNList), and Samsung Tsinghua Joint Laboratory.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yang, X., Liu, G., Deng, S. et al. Exploration of a mechanism to form bionic, self-growing and self-organizing neural network. Artif Intell Rev 52, 585–605 (2019). https://doi.org/10.1007/s10462-018-9626-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-018-9626-2