リケラボ論文検索は、全国の大学リポジトリにある学位論文・教授論文を一括検索できる論文検索サービスです。

リケラボ 全国の大学リポジトリにある学位論文・教授論文を一括検索するならリケラボ論文検索大学・研究所にある論文を検索できる

リケラボ 全国の大学リポジトリにある学位論文・教授論文を一括検索するならリケラボ論文検索大学・研究所にある論文を検索できる

大学・研究所にある論文を検索できる 「Artificial Visual System for Orientation Detection」の論文概要。リケラボ論文検索は、全国の大学リポジトリにある学位論文・教授論文を一括検索できる論文検索サービスです。
リケラボ

コピーが完了しました

URLをコピーしました

論文の公開元へ論文の公開元へ
書き出し

Artificial Visual System for Orientation Detection

叶 嘉蓁 富山大学

2022.09.28

概要

The human visual system is one of the most important component of the nervous system that provides visual perception to person. The research on orientation detection which neurons of the visual cortex response only to a line stimulus in a particular orientation is an important driving force of computer vision and biological vision. However, the prin- ciple of orientation detection remains a mystery. In this paper, we first propose a new orientation detection mechanism based on local orientation detective neurons’ dendritic computation. We assume that there be orientation detective neurons which response only to a particular orientation locally and these neurons detect local orientation infor- mation based on nonlinear interactions took place on the dendrites. Then, we propose an implementation of such local orientation detective neurons with dendritic neurons, use them to extract the local orientation information, and infer the global orientation infor- mation from these local orientation information. Based on the mechanism, we propose an Artificial Visual System (AVS) for orientation detection and other visual information processing. In order to prove the effectiveness of our mechanism and the Artificial Vis- ual System (AVS), we conduct a series of experiments which include objects with vari- ous sizes, shapes and positions. Computer simulation shows that the mechanism can perfectly perform orientation detection independent on their sizes, shapes and positions in all experiments. The experimental results are consistent well with the results of most known physiological experiments. Furthermore, we compare the performance of both Artificial Visual System (AVS) and Convolution Neural Network (CNN) on orientation detection and find that Artificial Visual System (AVS) completely beat Convolution Neural Network (CNN) on orientation detection in identification accuracy, noise re- sistance, computation and learning cost, hardware implementation and reasonability.


Secondly, based on the mechanism mentioned above, we use a single-layer McCulloch- Pitts neurons to realize such local orientation-sensitive neurons and show that such a single-layer perceptron artificial visual system (AVS) is capable of detecting global ori- entation by taking the orientation with the largest number of activations of the orienta- tion-selective neurons as the global orientation. We perform computer simulations on this single-layer perceptron AVS, and simulation results show that this single-layer per- ceptron AVS works perfectly for global orientation detection, which is consistent with most of physiological experiments and models. Furthermore, in order to show the supe- riority of the single-layer perceptron AVS, we compare the performance of the single- layer perceptron AVS with traditional convolutional neural network (CNN) on orienta- tion detection tasks and find that the single-layer perceptron AVS completely beats CNN in all aspects including identification accuracy, noise resistance, computational and learning cost, hardware implementation reasonability and bio-soundness.

Finally, as an important category of computational intelligence, meta-heuristic algo- rithms have always been a popular research interests over recent two decades. Teach- ing-learning- based optimization (TLBO) is one of nature-inspired meta-heuristic algo- rithm which is proven to have effectiveness and efficiency in solving complex optimiza- tion problems. Although TLBO has remarkable capacity to solve different optimization problems, but the issue of trapping into local optimal is a common drawback of meta- heuristic algorithm, and TLBO is no exception. Thus we use a novel search strategy to improve the performance of TLBO by means of a new selection operation. We select twenty-nine benchmark functions of IEEE CEC2017 to testify the performance of pro- posed algorithm in terms of effectiveness and robustness. Experimental results exhibit that the proposed algorithm outperforms other state-of-the-art algorithms.

論文の公開元へ

この論文で使われている画像

関連論文

関連論文をもっと見る

参考文献

[1] Hagai Agmon-Snir, Catherine E Carr, and John Rinzel. The role of dendrites in auditory coincidence detection. Nature, 393(6682):268–272, 1998.

[2] Qeethara Kadhim Al-Shayea. Artificial neural networks in medical diagnosis. Interna- tional Journal of Computer Science Issues, 8(2):150–154, 2011.

[3] James S Albus. A theory of cerebellar function. Mathematical biosciences, 10(1-2):25– 61, 1971.

[4] JC Anderson, T Binzegger, O Kahana, KAC Martin, and I Segev. Dendritic asym- metry cannot account for directional responses of neurons in visual cortex. Nature neuroscience, 2(9):820–824, 1999.

[5] Alain Artola, S Br¨ocher, and Wolf Singer. Different voltage-dependent thresholds for inducing long-term depression and long-term potentiation in slices of rat visual cortex. Nature, 347(6288):69–72, 1990.

[6] Guo-qiang Bi and Mu-ming Poo. Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type. Journal of neuroscience, 18(24):10464–10472, 1998.

[7] Barbara Chapman, Kathleen R Zahs, and Michael P Stryker. Relation of cortical cell orientation selectivity to alignment of receptive fields of the geniculocortical afferents that arborize within a single orientation column in ferret visual cortex. Journal of Neuroscience, 11(5):1347–1358, 1991.

[8] Chong Chen and Susumu Tonegawa. Molecular genetic analysis of synaptic plasticity, activity-dependent neural development, learning, and memory in the mammalian brain. Annual review of neuroscience, 20(1):157–184, 1997.

[9] Jiujun Cheng, Minjun Chen, MengChu Zhou, Shangce Gao, Chunmei Liu, and Cong Liu. Overlapping community change-point detection in an evolving network. IEEE Transactions on Big Data, 6(1):189–200, 2018.

[10] JiuJun Cheng, JunLu Cheng, MengChu Zhou, FuQiang Liu, ShangCe Gao, and Cong Liu. Routing in internet of vehicles: A review. IEEE Transactions on Intelligent Transportation Systems, 16(5):2339–2352, 2015.

[11] Jiujun Cheng, Xiao Wu, Mengchu Zhou, Shangce Gao, Zhenhua Huang, and Cong Liu. A novel method for detecting new overlapping community in complex evolving networks. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 49(9):1832– 1844, 2018.

[12] Jiujun Cheng, Guiyuan Yuan, MengChu Zhou, Shangce Gao, Cong Liu, and Hua Duan. A fluid mechanics-based data flow model to estimate vanet capacity. IEEE Transactions on Intelligent Transportation Systems, 21(6):2603–2614, 2019.

[13] Hongwei Dai, Yu Yang, Cunhua Li, Jun Shi, Shangce Gao, and Zheng Tang. Quantum interference crossover-based clonal selection algorithm and its application to traveling salesman problem. IEICE TRANSACTIONS on Information and Systems, 92(1):78– 85, 2009.

[14] Hans C Dringenberg, Bana Hamze, Amanda Wilson, William Speechley, and Min- Ching Kuo. Heterosynaptic facilitation of in vivo thalamocortical long-term potenti- ation in the adult rat visual cortex by acetylcholine. Cerebral Cortex, 17(4):839–848, 2007.

[15] Andries P Engelbrecht. Computational intelligence: an introduction. John Wiley & Sons, 2007.

[16] Thomas Euler, Peter B Detwiler, and Winfried Denk. Directionally selective calcium signals in dendrites of starburst amacrine cells. Nature, 418(6900):845–852, 2002.

[17] Pierre A Fortier and Chelsea Bray. Influence of asymmetric attenuation of single and paired dendritic inputs on summation of synaptic potentials and initiation of action potentials. Neuroscience, 236:195–209, 2013.

[18] Shelley I Fried, Thomas A Mu¨nch, and Frank S Werblin. Mechanisms and circuitry underlying directional selectivity in the retina. Nature, 420(6914):411–414, 2002.

[19] Shangce Gao, Shuangbao Song, Jiujun Cheng, Yuki Todo, and Mengchu Zhou. In- corporation of solvent effect into multi-objective evolutionary algorithm for improved protein structure prediction. IEEE/ACM transactions on computational biology and bioinformatics, 15(4):1365–1378, 2017.

[20] Shangce Gao, Zheng Tang, Hongwei Dai, and Jianchen Zhang. An improved clonal selection algorithm and its application to traveling salesman problems. IEICE transactions on fundamentals of electronics, communications and computer sciences, 90(12):2930–2938, 2007.

[21] Shangce Gao, Wei Wang, Hongwei Dai, Fangjia Li, and Zheng Tang. Improved clonal selection algorithm combined with ant colony optimization. IEICE transactions on information and systems, 91(6):1813–1823, 2008.

[22] Shangce Gao, Yirui Wang, Jiujun Cheng, Yasuhiro Inazumi, and Zheng Tang. Ant colony optimization with clustering for solving the dynamic location routing problem. Applied Mathematics and Computation, 285:149–173, 2016.

[23] Shangce Gao, Yang Yu, Yirui Wang, Jiahai Wang, Jiujun Cheng, and MengChu Zhou. Chaotic local search-based differential evolution algorithms for optimization. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 51(6):3954–3967, 2019.

[24] Shangce Gao, Mengchu Zhou, Yirui Wang, Jiujun Cheng, Hanaki Yachi, and Jiahai Wang. Dendritic neuron model with effective learning algorithms for classification, approximation, and prediction. IEEE transactions on neural networks and learning systems, 30(2):601–614, 2018.

[25] Wulfram Gerstner, Richard Kempter, J Leo Van Hemmen, and Hermann Wagner. A neuronal learning rule for sub-millisecond temporal coding. Nature, 383(6595):76–78, 1996.

[26] Albert Gidon, Timothy Adam Zolnik, Pawel Fidzinski, Felix Bolduan, Athanasia Pa- poutsi, Panayiota Poirazi, Martin Holtkamp, Imre Vida, and Matthew Evan Larkum. Dendritic action potentials and computation in human layer 2/3 cortical neurons. Sci- ence, 367(6473):83–87, 2020.

[27] Charles D Gilbert and Wu Li. Adult visual cortical plasticity. Neuron, 75(2):250–264, 2012.

[28] Nace L Golding and Nelson Spruston. Dendritic sodium spikes are variable triggers of axonal action potentials in hippocampal ca1 pyramidal neurons. Neuron, 21(5):1189– 1200, 1998.

[29] Erkam Guresen, Gulgun Kayakutlu, and Tugrul U Daim. Using artificial neural net- work models in stock market index prediction. Expert Systems with Applications, 38(8):10389–10397, 2011.

[30] Mohamad H Hassoun et al. Fundamentals of artificial neural networks. MIT press, 1995.

[31] Michael Hausser, Nelson Spruston, and Greg J Stuart. Diversity and dynamics of dendritic signaling. Science, 290(5492):739–744, 2000.

[32] Donald Olding Hebb. The organization of behavior: A neuropsychological theory. Psy- chology Press, 2005.

[33] Anthony Holtmaat and Karel Svoboda. Experience-dependent structural synaptic plas- ticity in the mammalian brain. Nature Reviews Neuroscience, 10(9):647–658, 2009.

[34] Kuo-lin Hsu, Hoshin Vijai Gupta, and Soroosh Sorooshian. Artificial neural network modeling of the rainfall-runoff process. Water resources research, 31(10):2517–2530, 1995.

[35] David H Hubel and Torsten N Wiesel. Receptive fields of single neurones in the cat’s striate cortex. The Journal of physiology, 148(3):574, 1959.

[36] David H Hubel and Torsten N Wiesel. Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. The Journal of physiology, 160(1):106, 1962.

[37] Masao Ito, Masaki Sakurai, and Pavich Tongroach. Climbing fibre induced depression of both mossy fibre responsiveness and glutamate sensitivity of cerebellar purkinje cells. The Journal of physiology, 324(1):113–134, 1982.

[38] Junkai Ji, Shangce Gao, Jiujun Cheng, Zheng Tang, and Yuki Todo. An approximate logic neuron model with a dendritic structure. Neurocomputing, 173:1775–1783, 2016.

[39] Junkai Ji, Shuangbao Song, Cheng Tang, Shangce Gao, Zheng Tang, and Yuki Todo. An artificial bee colony algorithm search guided by scale-free networks. Information Sciences, 473:142–165, 2019.

[40] Junkai Ji, Shuangbao Song, Yajiao Tang, Shangce Gao, Zheng Tang, and Yuki Todo. Approximate logic neuron model trained by states of matter search algorithm. Knowledge-Based Systems, 163:120–130, 2019.

[41] Tao Jiang, Shangce Gao, Dizhou Wang, Junkai Ji, Yuki Todo, and Zheng Tang. A neuron model with synaptic nonlinearities in a dendritic tree for liver disorders. IEEJ Transactions on Electrical and Electronic Engineering, 12(1):105–115, 2017.

[42] Tao Jiang, Shangce Gao, Dizhou Wang, Junkai Ji, Yuki Todo, and Zheng Tang. A neuron model with synaptic nonlinearities in a dendritic tree for liver disorders. IEEJ Transactions on Electrical and Electronic Engineering, 12(1):105–115, 2017.

[43] Jianzhong Jin, Yushi Wang, Harvey A Swadlow, and Jose M Alonso. Population receptive fields of on and off thalamic inputs to an orientation column in visual cortex. Nature neuroscience, 14(2):232–238, 2011.

[44] Eric R Kandel, James H Schwartz, Thomas M Jessell, Steven Siegelbaum, A James Hudspeth, Sarah Mack, et al. Principles of neural science, volume 4. McGraw-hill New York, 2000.

[45] Dervis Karaboga and Bahriye Basturk. A powerful and efficient algorithm for nu- merical function optimization: artificial bee colony (abc) algorithm. Journal of global optimization, 39(3):459–471, 2007.

[46] Adam Kepecs, Xiao-Jing Wang, and John Lisman. Bursting neurons signal input slope. Journal of Neuroscience, 22(20):9053–9062, 2002.

[47] Mehdi Khashei and Mehdi Bijari. An artificial neural network (p, d, q) model for timeseries forecasting. Expert Systems with applications, 37(1):479–489, 2010.

[48] Christof Koch. Biophysics of computation: information processing in single neurons. Oxford university press, 2004.

[49] Christof Koch, Tomaso Poggio, and Vincent Torre. Retinal ganglion cells: a functional interpretation of dendritic morphology. Philosophical Transactions of the Royal Society of London. B, Biological Sciences, 298(1090):227–263, 1982.

[50] Christof Koch, Tomaso Poggio, and Vincent Torre. Nonlinear interactions in a den- dritic tree: localization, timing, and role in information processing. Proceedings of the National Academy of Sciences, 80(9):2799–2802, 1983.

[51] Satoru Kondo, Takashi Yoshida, and Kenichi Ohki. Mixed functional microarchitec- tures for orientation selectivity in the mouse primary visual cortex. Nature communi- cations, 7(1):1–16, 2016.

[52] Yann LeCun, L´eon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learn- ing applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.

[53] Michael London and Michael H¨ausser. Dendritic computation. Annu. Rev. Neurosci., 28:503–532, 2005.

[54] Jeffrey C Magee. Dendritic integration of excitatory synaptic input. Nature Reviews Neuroscience, 1(3):181–190, 2000.

[55] David Marr and W Thomas Thach. A theory of cerebellar cortex. In From the Retina to the Neocortex, pages 11–50. Springer, 1991.

[56] Marco Martina, Imre Vida, and Peter Jonas. Distal initiation and active propagation of action potentials in interneuron dendrites. Science, 287(5451):295–300, 2000.

[57] Warren S McCulloch and Walter Pitts. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4):115–133, 1943.

[58] David McLaughlin, Robert Shapley, Michael Shelley, and Dingeman J Wielaard. A neuronal network model of macaque primary visual cortex (v1): Orientation selectivity and dynamics in the input layer 4cα. Proceedings of the National Academy of Sciences, 97(14):8087–8092, 2000.

[59] Seyedali Mirjalili. Sca: a sine cosine algorithm for solving optimization problems. Knowledge-based systems, 96:120–133, 2016.

[60] Seyedali Mirjalili, Seyed Mohammad Mirjalili, and Andrew Lewis. Grey wolf optimizer. Advances in engineering software, 69:46–61, 2014.

[61] Michael A Nielsen. Neural networks and deep learning, volume 25. Determination press San Francisco, CA, USA, 2015.

[62] Albert B Novikoff. On convergence proofs for perceptrons. Technical report, STAN- FORD RESEARCH INST MENLO PARK CA, 1963.

[63] Nicholas Oesch, Thomas Euler, and W Rowland Taylor. Direction-selective dendritic action potentials in rabbit retina. Neuron, 47(5):739–750, 2005.

[64] Matteo Poggi and Stefano Mattoccia. Learning from scratch a confidence measure. In Bmvc, volume 2, page 4, 2016.

[65] Panayiota Poirazi, Terrence Brannon, and Bartlett W Mel. Pyramidal neuron as two- layer neural network. Neuron, 37(6):989–999, 2003.

[66] Nicholas J Priebe and David Ferster. Mechanisms of neuronal computation in mam- malian visual cortex. Neuron, 75(2):194–208, 2012.

[67] R Venkata Rao, Vimal J Savsani, and DP Vakharia. Teaching–learning-based opti- mization: a novel method for constrained mechanical design optimization problems. Computer-aided design, 43(3):303–315, 2011.

[68] Frank Rosenblatt. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, 65(6):386, 1958.

[69] Peter C Schwindt and Wayne E Crill. Local and propagated dendritic action potentials evoked by glutamate iontophoresis on rat neocortical pyramidal neurons. Journal of Neurophysiology, 77(5):2466–2483, 1997.

[70] Idan Segev and Wilfrid Rall. Excitable dendrites and spines: earlier theoretical insights elucidate recent direct observations. Trends in neurosciences, 21(11):453–460, 1998.

[71] Y Sekiya, T Aoyama, T Hiroki, and T Zheng. Learningpossibility that neuron model can recognize depth-rotation in threedimension. In Proc. of 1st International Confer- ence on Control Automation and Systems, page 149, 2001.

[72] R Angus Silver. Neuronal arithmetic. Nature Reviews Neuroscience, 11(7):474–489, 2010.

[73] Sandra Single and Alexander Borst. Dendritic integration and its role in computing image velocity. Science, 281(5384):1848–1850, 1998.

[74] Shuangbao Song, Shangce Gao, Xingqian Chen, Dongbao Jia, Xiaoxiao Qian, and Yuki Todo. Aimoes: Archive information assisted multi-objective evolutionary strategy for ab initio protein structure prediction. Knowledge-Based Systems, 146:58–72, 2018.

[75] Greg Stuart, Nelson Spruston, Bert Sakmann, and Michael H¨ausser. Action potential initiation and backpropagation in neurons of the mammalian cns. Trends in neuro- sciences, 20(3):125–131, 1997.

[76] Greg J Stuart and Nelson Spruston. Dendritic integration: 60 years of progress. Nature neuroscience, 18(12):1713–1721, 2015.

[77] Deyu Tang. Spherical evolution for solving continuous optimization problems. Applied Soft Computing, 81:105499, 2019.

[78] Yajiao Tang, Junkai Ji, Yulin Zhu, Shangce Gao, Zheng Tang, and Yuki Todo. A differential evolution-oriented pruning neural network model for bankruptcy prediction. Complexity, 2019, 2019.

[79] Zheng Tang, Hiroki Tamura, Makoto Kuratu, Okihiko Ishizuka, and Koichi Tanno. A model of the neuron based on dendrite mechanisms. Electronics and Communications in Japan (Part III: Fundamental Electronic Science), 84(8):11–24, 2001.

[80] W Rowland Taylor, Shigang He, William R Levick, and David I Vaney. Dendritic computation of direction selectivity by retinal ganglion cells. Science, 289(5488):2347– 2350, 2000.

[81] W Rowland Taylor and David I Vaney. New directions in retinal research. Trends in neurosciences, 26(7):379–385, 2003.

[82] Yuki Todo, Hiroki Tamura, Kazuya Yamashita, and Zheng Tang. Unsupervised learn- able neuron model with nonlinear interaction on dendrites. Neural Networks, 60:96–103, 2014.

[83] Yuki Todo, Zheng Tang, Hiroyoshi Todo, Junkai Ji, and Kazuya Yamashita. Neurons with multiplicative interactions of nonlinear synapses. International journal of neural systems, 29(08):1950012, 2019.

[84] Catherine Vairappan, Hiroki Tamura, Shangce Gao, and Zheng Tang. Batch type local search-based adaptive neuro-fuzzy inference system (anfis) with self-feedbacks for time-series prediction. Neurocomputing, 72(7-9):1870–1877, 2009.

[85] Toby J Velte and Richard H Masland. Action potentials in the dendrites of retinal ganglion cells. Journal of neurophysiology, 81(3):1412–1417, 1999.

[86] Jiahai Wang, Binzhong Cen, Shangce Gao, Zizhen Zhang, and Yuren Zhou. Coop- erative evolutionary framework with focused search for many-objective optimization. IEEE Transactions on Emerging Topics in Computational Intelligence, 4(3):398–412, 2018.

[87] Wei Wang, Shangce Gao, and Zheng Tang. Improved pattern recognition with complex artificial immune system. Soft Computing, 13(12):1209–1217, 2009.

[88] Yirui Wang, Yang Yu, Shuyang Cao, Xingyi Zhang, and Shangce Gao. A review of applications of artificial intelligent algorithms in wind farms. Artificial Intelligence Review, 53(5):3447–3500, 2020.

[89] Daniel E Wilson, David E Whitney, Benjamin Scholl, and David Fitzpatrick. Ori- entation selectivity and the functional clustering of synaptic inputs in primary visual cortex. Nature neuroscience, 19(8):1003–1009, 2016.

[90] Zhe Xu, Yirui Wang, Sheng Li, Yanting Liu, Yuki Todo, and Shangce Gao. Immune algorithm combined with estimation of distribution for traveling salesman problem. IEEJ Transactions on Electrical and Electronic Engineering, 11:S142–S154, 2016.

[91] Santiago Ram´on y Cajal. Histologie du syst`eme nerveux de l’homme & des vert´ebr´es: Cervelet, cerveau moyen, r´etine, couche optique, corps stri´e, ´ecorce c´er´ebrale g´en´erale & r´egionale, grand sympathique, volume 2. A. Maloine, 1911.

[92] Gang Yang, Junyan Yi, Shangce Gao, and Zheng Tang. An improved transiently chaotic neural network with multiple chaotic dynamics for maximum clique problem. In Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007), pages 275–275. IEEE, 2007.

[93] Yang Yu, Shangce Gao, Yirui Wang, and Yuki Todo. Global optimum-based search differential evolution. IEEE/CAA Journal of Automatica Sinica, 6(2):379–394, 2019.

[94] Ming-Yuan Zhao, KE Tang, Gang Lu, Ming-Tian Zhou, Chong Fu, Fan Yang, and Cheng-Gong Zhang. A novel clonal selection algorithm and its application. In 2008 International Conference on Apperceiving Computing and Intelligence Analysis, pages 385–388. IEEE, 2008.

[95] Tianle Zhou, Shangce Gao, Jiahai Wang, Chaoyi Chu, Yuki Todo, and Zheng Tang. Financial time series prediction using a dendritic neuron model. Knowledge-Based Systems, 105:214–224, 2016.

[96] Tianle Zhou, Shangce Gao, Jiahai Wang, Chaoyi Chu, Yuki Todo, and Zheng Tang. Financial time series prediction using a dendritic neuron model. Knowledge-Based Systems, 105:214–224, 2016.

参考文献をもっと見る

全国の大学の
卒論・修論・学位論文
を
一発検索！

この論文の関連論文を見る