【摘要】：Spiking神經(jīng)網(wǎng)絡(luò)作為新一代人工神經(jīng)網(wǎng)絡(luò),其時間編碼的計算優(yōu)勢使其在研究領(lǐng)域的影響力與日俱增。在視覺神經(jīng)系統(tǒng)的模擬層面,建立恰當(dāng)?shù)挠嬎隳Ｐ鸵阅M視網(wǎng)膜神經(jīng)元的圖像特征提取方式,并采用高效的學(xué)習(xí)算法對信息進(jìn)行處理,一直是Spiking神經(jīng)網(wǎng)絡(luò)研究領(lǐng)域具有前瞻性和實用性的研究方向。本文在分析Spiking神經(jīng)網(wǎng)絡(luò)基本模型的基礎(chǔ)上,從人類和靈長類動物模式識別的認(rèn)知研究中得到了靈感,著眼于Spiking神經(jīng)網(wǎng)絡(luò)的經(jīng)典學(xué)習(xí)規(guī)則以及神經(jīng)網(wǎng)絡(luò)圖像特征提取技術(shù),研究了基于Spiking神經(jīng)網(wǎng)絡(luò)的學(xué)習(xí)算法和圖像特征提取技術(shù)的應(yīng)用問題,主要包括以下內(nèi)容:(1)研究并提出了一種具有良好特征表示的圖像特征提取方法,該方法根據(jù)Spiking神經(jīng)網(wǎng)絡(luò)的特點改進(jìn)了相位延遲編碼方法對圖像特征進(jìn)行了轉(zhuǎn)化。相位延遲編碼作為Spiking神經(jīng)網(wǎng)絡(luò)常用的特征表示方法,具有很強(qiáng)的特征表達(dá)能力和生物可行性。通過對生物神經(jīng)系統(tǒng)的體系結(jié)構(gòu)、編碼方式和學(xué)習(xí)理論的研究,我們考慮了外部刺激及不應(yīng)期等多種因素,特征被最終轉(zhuǎn)化為脈沖序列。通過信息的轉(zhuǎn)換,圖像自身攜帶的信息得以保留,取得了很好的特征提取效果。(2)在對經(jīng)典膜電壓函數(shù)相關(guān)的Spiking神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)算法進(jìn)行分析的基礎(chǔ)上,改進(jìn)了一種膜電壓驅(qū)動的監(jiān)督學(xué)習(xí)算法。該算法以目標(biāo)輸出脈沖時間點為標(biāo)準(zhǔn),將學(xué)習(xí)情況分為目標(biāo)輸出脈沖時間點和非目標(biāo)輸出脈沖時間點進(jìn)行約束和篩選,以提升學(xué)習(xí)的效率。算法通過減少圖像特征的維度,在算法效率上要明顯優(yōu)于同類經(jīng)典算法,而在膜電壓背景噪聲和輸入抖動噪聲存在的情況下,其魯棒性也具有相當(dāng)?shù)膬?yōu)勢。(3)提出了一種基于Spiking神經(jīng)網(wǎng)絡(luò)的圖像識別新模型,新模型具有識別效率高,仿生性能好,魯棒性強(qiáng)等特點。模型對圖像特征進(jìn)行了高效提取,保留了圖像中關(guān)鍵的邊緣信息和紋理信息,使用了更高效的學(xué)習(xí)算法處理輸入模式的訓(xùn)練問題。整個模型從認(rèn)知神經(jīng)學(xué)的角度入手,猜想并模擬了生物神經(jīng)網(wǎng)絡(luò)從視覺輸入到認(rèn)知判斷的過程,將理論應(yīng)用到圖像模式識別的具體問題上,通過對生物和計算科學(xué)的理論補充,完成了基礎(chǔ)計算模型的建立。
[Abstract]:As a new generation of artificial neural network, Spiking neural network has more and more influence in the field of research because of its computational advantage of time coding. At the level of visual nervous system simulation, an appropriate computational model is established to simulate the image feature extraction of retinal neurons, and an efficient learning algorithm is used to process the information. It has always been a prospective and practical research direction in the field of Spiking neural network research. Based on the analysis of the basic model of Spiking neural network, this paper draws inspiration from the cognitive research of human and primate pattern recognition, focusing on the classical learning rules of Spiking neural network and the feature extraction technology of neural network image. The application of learning algorithm and image feature extraction technology based on Spiking neural network is studied. The main contents are as follows: (1) an image feature extraction method with good feature representation is proposed. According to the characteristics of Spiking neural network, the phase delay coding method is improved to transform the image features. As a common feature representation method of Spiking neural network, phase delay coding has strong feature expression ability and biological feasibility. Through the study of the system structure, coding mode and learning theory of the biological nervous system, we considered the external stimulation and the refractory period, and the characteristics were transformed into pulse sequence. Through the transformation of information, the information carried by the image itself can be preserved, and a good feature extraction effect is obtained. (2) based on the analysis of the Spiking neural network learning algorithm related to the classical membrane voltage function, A supervised learning algorithm for membrane voltage drive is improved. The algorithm takes the target output pulse time point as the standard, and divides the learning situation into target output pulse time point and non-target output pulse time point for constraint and selection, in order to improve the learning efficiency. By reducing the dimension of image features, the algorithm is more efficient than other classical algorithms, and when the voltage background noise and the input jitter noise exist, Its robustness also has some advantages. (3) A new image recognition model based on Spiking neural network is proposed. The new model is characterized by high recognition efficiency, good bionic performance and strong robustness. The model extracts the image features efficiently, preserves the key edge information and texture information in the image, and uses a more efficient learning algorithm to deal with the training problem of input pattern. The whole model starts from the perspective of cognitive neurology, conjectures and simulates the process of biological neural network from visual input to cognitive judgment, applies the theory to the specific problems of image pattern recognition, and complements the theory of biology and computational science. The foundation calculation model is established.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.41;TP181

【參考文獻(xiàn)】

相關(guān)期刊論文 前9條

1 曾曉勤;何嘉晟;;單隱層感知機(jī)神經(jīng)網(wǎng)絡(luò)對權(quán)擾動的敏感性計算[J];河海大學(xué)學(xué)報(自然科學(xué)版);2013年04期

2 陳浩;吳慶祥;王穎;林梅燕;蔡榮太;;基于脈沖神經(jīng)網(wǎng)絡(luò)模型的車輛車型識別[J];計算機(jī)系統(tǒng)應(yīng)用;2011年04期

3 王義萍;陳慶偉;胡維禮;;基底神經(jīng)節(jié)的尖峰神經(jīng)元網(wǎng)絡(luò)模型及其在機(jī)器人中的應(yīng)用[J];南京理工大學(xué)學(xué)報(自然科學(xué)版);2010年06期

4 蔡榮太;吳慶祥;;基于脈沖神經(jīng)網(wǎng)絡(luò)的紅外目標(biāo)提取[J];計算機(jī)應(yīng)用;2010年12期

5 蔡榮太;吳慶祥;王平;;脈沖神經(jīng)元的信息處理[J];計算機(jī)與現(xiàn)代化;2010年11期

6 蔡榮太;吳慶祥;;基于脈沖神經(jīng)網(wǎng)絡(luò)的邊緣檢測[J];微電子學(xué)與計算機(jī);2010年10期

7 曹平;陳盼;章文彬;張潮;;基于脈沖神經(jīng)網(wǎng)絡(luò)的語音識別方法的初步探究[J];計算機(jī)工程與科學(xué);2008年04期

8 沈虹;;基于Spiking神經(jīng)網(wǎng)絡(luò)的蛋白質(zhì)二級結(jié)構(gòu)學(xué)習(xí)預(yù)測模型[J];電腦知識與技術(shù)(學(xué)術(shù)交流);2007年21期

9 彭建華;呂曉莉;劉延柱;;脈動型神經(jīng)元網(wǎng)絡(luò)的聯(lián)想記憶與分割[J];計算力學(xué)學(xué)報;2006年02期

相關(guān)碩士學(xué)位論文 前2條

1 潘婷;Spiking神經(jīng)網(wǎng)絡(luò)及其在圖像處理技術(shù)上的應(yīng)用研究[D];電子科技大學(xué);2015年

2 章文彬;基于脈沖神經(jīng)網(wǎng)絡(luò)的語音識別方法研究[D];浙江工業(yè)大學(xué);2007年

，

本文編號：2156416