【摘要】：1971年,蔡少棠教授通過(guò)電路理論的完備性提出了憶阻器的概念,它具有一系列的優(yōu)良特性,如納米級(jí)尺寸、非線(xiàn)性特性、掉電后信息非易失性等。因而在信息存儲(chǔ)、控制電路、非線(xiàn)性電路、人工神經(jīng)網(wǎng)絡(luò)等領(lǐng)域有著廣泛的應(yīng)用前景。隨著信息化時(shí)代的不斷發(fā)展,人們迫切需要更加智能化和微型化的信息處理系統(tǒng),通過(guò)模擬大腦神經(jīng)系統(tǒng)構(gòu)造人工神經(jīng)網(wǎng)絡(luò),提供了可行的解決方案,并且一直是科學(xué)研究的一個(gè)熱門(mén)領(lǐng)域。憶阻器的記憶特性類(lèi)似于大腦神經(jīng)網(wǎng)絡(luò)中的突觸功能,利用憶阻器有望構(gòu)建更具仿生智能的神經(jīng)網(wǎng)絡(luò)系統(tǒng),從而加速信息化處理的能力。本文針對(duì)憶阻值漂移現(xiàn)象,基于誤差原理分析和實(shí)驗(yàn)論證,證明了利用雙極性脈沖能夠有效減少憶阻值漂移造成的誤差。同時(shí),設(shè)計(jì)了能夠產(chǎn)生大小相等、極性相反對(duì)稱(chēng)脈沖的雙極性脈沖電路,并將其應(yīng)用于神經(jīng)突觸和神經(jīng)網(wǎng)絡(luò)。進(jìn)一步,通過(guò)分析神經(jīng)元和神經(jīng)突觸的原理,討論設(shè)計(jì)了更加靈活的神經(jīng)網(wǎng)絡(luò)電路實(shí)現(xiàn)。本文主要工作包含了以下內(nèi)容:(1)介紹了憶阻器模擬突觸的原理和可行性,隨后,分析了憶阻串并聯(lián)電路的特性,包括串聯(lián)結(jié)構(gòu)和并聯(lián)結(jié)構(gòu)�；趹涀杵骱�(jiǎn)單組合電路,進(jìn)一步分析了憶阻橋突觸電路的原理特性,包括四個(gè)憶阻器和五個(gè)憶阻器構(gòu)成的橋突觸結(jié)構(gòu)。最后,結(jié)合細(xì)胞神經(jīng)網(wǎng)絡(luò)和憶阻橋突觸結(jié)構(gòu),介紹了憶阻橋神經(jīng)網(wǎng)絡(luò)的結(jié)構(gòu)和特點(diǎn)。(2)分析了憶阻橋模擬神經(jīng)突觸的原理,并分別討論了線(xiàn)性和非線(xiàn)性惠普憶阻器模型下,突觸模擬過(guò)程中產(chǎn)生的憶阻器阻值漂移現(xiàn)象。由于憶阻值漂移現(xiàn)象,會(huì)導(dǎo)致一定程度的模擬誤差,推導(dǎo)了憶阻值漂移產(chǎn)生的機(jī)理,提出了用雙極性脈沖的對(duì)稱(chēng)性減少這種誤差�；诖嗽O(shè)計(jì)了一種產(chǎn)生對(duì)稱(chēng)脈沖信號(hào)電路,將其用于憶阻器突觸,減少了突觸模擬誤差,并進(jìn)行了數(shù)值分析和仿真比較,驗(yàn)證了所提出方法的有效性。(3)基于雙極性脈沖發(fā)生器的憶阻突觸結(jié)構(gòu),將其與細(xì)胞神經(jīng)網(wǎng)絡(luò)相結(jié)合,構(gòu)造優(yōu)化的憶阻突觸神經(jīng)網(wǎng)絡(luò)。由于減少了憶阻值漂移造成的誤差,它的突觸權(quán)值模擬更為精確。在細(xì)胞神經(jīng)網(wǎng)絡(luò)中,利用模板算子和圖像像素的二值進(jìn)行卷積能夠?qū)崿F(xiàn)一些圖像處理功能,這種模板算子通常是數(shù)值構(gòu)成的矩陣形式,因此將突觸權(quán)值對(duì)應(yīng)細(xì)胞神經(jīng)網(wǎng)絡(luò)進(jìn)行圖像處理中的模板算子,能夠?qū)崿F(xiàn)圖像處理能力。與傳統(tǒng)神經(jīng)網(wǎng)絡(luò)處理能力相比,本文中優(yōu)化的神經(jīng)網(wǎng)絡(luò)顯示出了更加優(yōu)越的圖像處理效果,通過(guò)Matlab仿真論證了該神經(jīng)網(wǎng)絡(luò)的有效性。(4)基于BP神經(jīng)算法,設(shè)計(jì)了新型憶阻橋神經(jīng)元與神經(jīng)突觸電路,它更靈活地實(shí)現(xiàn)了突觸權(quán)值的更新。最后,構(gòu)建了更加靈活的神經(jīng)網(wǎng)絡(luò)電路結(jié)構(gòu),通過(guò)巴普洛夫聯(lián)想記憶實(shí)驗(yàn)仿真論證了該神經(jīng)網(wǎng)絡(luò)能夠?qū)崿F(xiàn)聯(lián)想記憶的能力。
[Abstract]:In 1971, Professor Cai Shaotang put forward the concept of resistive device through the completeness of circuit theory. It has a series of excellent characteristics, such as nanometer size, nonlinear characteristics, non-volatile information after power down, and so on. Therefore, it has a wide application prospect in the fields of information storage, control circuit, nonlinear circuit, artificial neural network and so on. With the continuous development of the information age, people urgently need more intelligent and miniature information processing system. Through simulating the neural system of the brain to construct artificial neural network, it provides a feasible solution. And has been a hot area of scientific research. The memory characteristics of the resistor are similar to the synaptic function in the neural network of the brain. It is expected that the memory device can be used to construct a more bionic intelligent neural network system so as to accelerate the ability of information processing. Aiming at the phenomenon of amnesia drift, based on the error principle analysis and experimental demonstration, it is proved that using bipolar pulse can effectively reduce the error caused by amnesia resistance drift. At the same time, a bipolar pulse circuit which can generate symmetrical pulses of equal size and opposite polarity is designed and applied to neural synapses and neural networks. Furthermore, by analyzing the principle of neuron and synapse, a more flexible neural network circuit is designed. The main contents of this thesis are as follows: (1) the principle and feasibility of analog synapse of amnesia are introduced. Then, the characteristics of series-parallel circuit are analyzed, including series structure and parallel structure. Based on the simple combinatorial circuit of the memory bridge, the principle characteristics of the bridge synaptic circuit are further analyzed, including the bridge synaptic structure composed of four memristors and five memristors. Finally, combined with cellular neural network and memory bridge synaptic structure, the structure and characteristics of amnesia bridge neural network are introduced. (2) the principle of amnesia simulated synapse is analyzed, and the linear and nonlinear models of Hewlett-Packard amnesia are discussed, respectively. The phenomenon of amnesia resistance drift during synaptic simulation. The phenomenon of amnesia drift will lead to a certain degree of simulation error. The mechanism of amnesia drift is deduced and the symmetry of bipolar pulse is proposed to reduce the error. Based on this, a symmetrical pulse signal circuit is designed, which is applied to the synapse of amnesia, which reduces the error of synapse simulation, and makes numerical analysis and simulation comparison. The effectiveness of the proposed method is verified. (3) based on the mnemonic synaptic structure of bipolar pulse generator, an optimized mnemonic synaptic neural network is constructed by combining it with cellular neural network. Because of reducing the error caused by amnesia resistance drift, its synaptic weight simulation is more accurate. In cellular neural networks, some image processing functions can be realized by convolution of template operator and binary value of image pixels. This kind of template operator is usually a matrix form of numerical value. Therefore, the image processing ability can be realized by using the template operator to correspond the synaptic weight to the cellular neural network. Compared with the traditional neural network processing ability, the optimized neural network in this paper shows more superior image processing effect. The effectiveness of the neural network is demonstrated by Matlab simulation. (4) based on the BP neural algorithm, A new type of synaptic circuit of amnesia bridge neuron and nerve is designed, which can update the synaptic weight more flexibly. Finally, a more flexible neural network circuit structure is constructed, and the ability of the neural network to realize associative memory is demonstrated by the experimental simulation of Pavlov's associative memory.
【學(xué)位授予單位】：西南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP183;TN60

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 王小平;陳敏;沈軼;;Switching mechanism for TiO_2 memristor and quantitative analysis of exponential model parameters[J];Chinese Physics B;2015年08期

2 武花干;包伯成;陳墨;;Threshold flux-controlled memristor model and its equivalent circuit implementation[J];Chinese Physics B;2014年11期

3 劉東青;程海峰;朱玄;王楠楠;張朝陽(yáng);;憶阻器及其阻變機(jī)理研究進(jìn)展[J];物理學(xué)報(bào);2014年18期

4 王麗丹;段美濤;段書(shū)凱;胡小方;;基于STDP規(guī)則和憶阻橋突觸的神經(jīng)網(wǎng)絡(luò)及圖像處理[J];中國(guó)科學(xué):信息科學(xué);2014年07期

5 徐暉;田曉波;步凱;李清江;;溫度改變對(duì)鈦氧化物憶阻器導(dǎo)電特性的影響[J];物理學(xué)報(bào);2014年09期

6 段書(shū)凱;胡小方;王麗丹;李傳東;MAZUMDER Pinaki;;憶阻器阻變隨機(jī)存取存儲(chǔ)器及其在信息存儲(chǔ)中的應(yīng)用[J];中國(guó)科學(xué):信息科學(xué);2012年06期

7 蔡坤鵬;王睿;周濟(jì);;第四種無(wú)源電子元件憶阻器的研究及應(yīng)用進(jìn)展[J];電子元件與材料;2010年04期

相關(guān)碩士學(xué)位論文 前1條

1 張鐸;憶阻器基本特性與基于憶阻器的生物突觸研究[D];電子科技大學(xué);2015年

，

本文編號(hào)：2359299