發(fā)布時(shí)間：2017-12-27 20:17

  本文關(guān)鍵詞：感知、協(xié)作與進(jìn)化—智能依賴于結(jié)構(gòu)和其上的運(yùn)動(dòng)　出處：《南京大學(xué)》2016年博士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 感知協(xié)作神經(jīng)網(wǎng)絡(luò) 感知進(jìn)化神經(jīng)網(wǎng)絡(luò) 人工進(jìn)化 皮質(zhì)-感受器人工擴(kuò)展

【摘要】：受生物學(xué)啟發(fā)的計(jì)算模型是促進(jìn)人工智能領(lǐng)域發(fā)展的重要推動(dòng)力。長(zhǎng)期以來,大量的學(xué)者根據(jù)生物現(xiàn)象提出了各種各樣的仿生計(jì)算模型,為人工智能領(lǐng)域做出了許多的開創(chuàng)性的貢獻(xiàn)。本文試圖跟隨這樣的足跡,調(diào)研了近些年一些生理學(xué)實(shí)驗(yàn)及發(fā)現(xiàn),并在此基礎(chǔ)上發(fā)現(xiàn),神經(jīng)系統(tǒng)的結(jié)構(gòu)以及神經(jīng)沖動(dòng)在神經(jīng)系統(tǒng)結(jié)構(gòu)上的運(yùn)動(dòng)模式對(duì)于生物體的智能行為有著至關(guān)重要的影響�？梢哉f,生物體的智能行為依賴于神經(jīng)系統(tǒng)的結(jié)構(gòu)和神經(jīng)沖動(dòng)在該結(jié)構(gòu)上的運(yùn)動(dòng)模式。在這種想法下,本文試圖模擬大腦的結(jié)構(gòu)、神經(jīng)沖動(dòng)在該結(jié)構(gòu)上的運(yùn)動(dòng)模式、以及這種結(jié)構(gòu)的開放性(或可擴(kuò)展性),提出了兩種仿生計(jì)算模型,即感知協(xié)作神經(jīng)網(wǎng)絡(luò)和感知進(jìn)化神經(jīng)網(wǎng)絡(luò)。主要工作如下：(1)為了模仿大腦對(duì)于不同感官感覺的協(xié)作,提出了感知協(xié)作神經(jīng)網(wǎng)絡(luò)。該網(wǎng)絡(luò)的建立受到大腦的層級(jí)結(jié)構(gòu)以及層級(jí)結(jié)構(gòu)中各部分功能單元相互協(xié)作的啟發(fā)。感知協(xié)作神經(jīng)網(wǎng)絡(luò)為層級(jí)結(jié)構(gòu),按照功能對(duì)應(yīng)于初級(jí)感覺區(qū)、初級(jí)感覺聯(lián)合區(qū)和高級(jí)聯(lián)合區(qū)。初級(jí)感覺區(qū)負(fù)責(zé)處理一些零碎的感覺,如顏色、形狀和音節(jié)等。初級(jí)感覺聯(lián)合區(qū)連接初級(jí)感覺區(qū)中零碎的感覺,形成表征單一物體的概念,如視覺實(shí)體概念、聽覺概念和味覺實(shí)體概念等。高級(jí)聯(lián)合區(qū)連接不同的初級(jí)感覺聯(lián)合區(qū),如視聽感覺、視味感覺的聯(lián)合等,即該區(qū)域執(zhí)行通感功能。感知協(xié)作神經(jīng)網(wǎng)絡(luò)對(duì)神經(jīng)元進(jìn)行了功能職責(zé)的劃分,包括特征神經(jīng)元、初級(jí)概念神經(jīng)元和聯(lián)合神經(jīng)元。不同類別的神經(jīng)元擁有不同的行為模式。感知進(jìn)化神經(jīng)網(wǎng)絡(luò)可以通過建立神經(jīng)元之間的突觸連接而快速形成新的記憶。無意識(shí)沖動(dòng)和內(nèi)省機(jī)制用以保證網(wǎng)絡(luò)結(jié)構(gòu)與外部數(shù)據(jù)結(jié)構(gòu)的一致性。該模型可以應(yīng)用于概念獲取、信息融合、在線學(xué)習(xí)系統(tǒng)、機(jī)器人系統(tǒng)等領(lǐng)域。(2)文獻(xiàn)[87]中的實(shí)驗(yàn)表明,cDNA基因敲入小鼠表現(xiàn)出增強(qiáng)的長(zhǎng)波長(zhǎng)光感知能力并獲得新的顏色辨別能力。該實(shí)驗(yàn)暗示了生物體的感知系統(tǒng)或神經(jīng)系統(tǒng)結(jié)構(gòu)是可以人工擴(kuò)展的,如利用[87]文中的基因工程技術(shù)。受到上述啟發(fā),本文提出如下問題：是否可以開發(fā)一個(gè)可以在線擴(kuò)展感知能力的智能主體,從而打破智能主體的感知限制。為解決這一問題,提出了感知進(jìn)化神經(jīng)網(wǎng)絡(luò),包括類型I，新型感受器加入已有感官和類型II，新型感官突現(xiàn)于智能體。當(dāng)新型感受器加入已有感官時(shí),新型感受器接受的刺激連同已有感受器接受的刺激傳入到初級(jí)感覺區(qū),此區(qū)域中的特征神經(jīng)元把從固有感受器提取的特征和從新型感受器提取的特征進(jìn)行聯(lián)合,從而形成更加深化的特征概念。即通過在特征神經(jīng)元和新型感受器之間建立突觸,使特征神經(jīng)元的響應(yīng)維度被在線擴(kuò)充。當(dāng)新型感官突現(xiàn)于智能體時(shí),新型感官感受器接受的刺激連同已有感官感受器接受的刺激傳入到初級(jí)感覺區(qū)并在此區(qū)域加工成零碎的感覺。這些零碎的感覺沿著網(wǎng)絡(luò)結(jié)構(gòu)向上傳導(dǎo)至初級(jí)感覺聯(lián)合區(qū),并在該區(qū)域激活響應(yīng)的概念神經(jīng)元。而后,概念神經(jīng)元將激活信號(hào)傳導(dǎo)至高級(jí)聯(lián)合區(qū),新型感官與已有感官將在此區(qū)域通過聯(lián)合神經(jīng)元進(jìn)行聯(lián)系,從而形成新型感官和固有感官的協(xié)作。該模型從計(jì)算的觀點(diǎn)出發(fā),部分回答了[87]文中關(guān)于“…創(chuàng)建額外類型的感覺神經(jīng)元或者促進(jìn)神經(jīng)回路的突現(xiàn),以比較新的和現(xiàn)有的感覺反應(yīng)”的問題。感知進(jìn)化神經(jīng)網(wǎng)絡(luò)可以應(yīng)用于信息融合、在線學(xué)習(xí)系統(tǒng)、機(jī)器人系統(tǒng)等領(lǐng)域。(3)種種神經(jīng)生理學(xué)實(shí)驗(yàn)[142,146,187]和醫(yī)學(xué)案例跡象表明大腦皮質(zhì)和生物體感受器是具有可擴(kuò)展能力的�；诟兄獏f(xié)作神經(jīng)網(wǎng)絡(luò)、感知進(jìn)化神經(jīng)網(wǎng)絡(luò)和這些神經(jīng)生理學(xué)實(shí)驗(yàn)以及醫(yī)學(xué)案例,本文提出了皮質(zhì)-感受器人工擴(kuò)展理論。基于該理論進(jìn)而提出人工進(jìn)化的概念,即人工進(jìn)化旨在通過感官-大腦重整和擴(kuò)展在生命體級(jí)別上實(shí)現(xiàn)進(jìn)化。雖然目前該概念和理論處于設(shè)想階段,但是這一概念和理論具有很好的可挖掘性,也同時(shí)具有很好的啟示性。感知協(xié)作神經(jīng)網(wǎng)絡(luò)和感知進(jìn)化神經(jīng)網(wǎng)絡(luò)旨在模擬生物的感知、協(xié)作以及進(jìn)化行為。文中實(shí)驗(yàn)初步驗(yàn)證了這兩種模型的有效性。然而,想要將這兩種模型投入到實(shí)際應(yīng)用中去,還有很長(zhǎng)的路要走。論文的后語部分討論了一些問題,主要集中在微觀的生理結(jié)構(gòu)和生理過程是如何和宏觀的智能行為進(jìn)行聯(lián)系。文中對(duì)于這些問題的討論雖然比較粗糙,但是這些都是值得深入思考的問題。希望這些問題可以有后續(xù)的理論化和工程化。
[Abstract]:The computational model inspired by biology is an important driving force in the development of artificial intelligence. For a long time, a large number of scholars have proposed a variety of bionic computing models based on biological phenomena, which have made many pioneering contributions to the field of artificial intelligence. This paper attempts to follow such a footprint and investigate some physiological experiments and findings in recent years. On this basis, it is found that the structure of the nervous system and the movement mode of nervous impulse on the nervous system structure have a crucial impact on the intelligent behavior of organism. It can be said that the intelligent behavior of the organism depends on the structure of the nervous system and the pattern of the movement of the nerve impulses on the structure. Under this idea, we try to simulate the brain's structure, the movement mode of nerve impulse on this structure, and the openness (or extensibility) of the structure. We propose two bionic computing models, namely the perceptive cooperative neural network and the perceptive evolutionary neural network. The main work is as follows: (1) in order to imitate the cooperation between the brain and different sensory senses, a cognitive cooperative neural network is proposed. The establishment of the network is inspired by the hierarchical structure of the brain and the collaboration of functional units in the hierarchical structure. The cognitive cooperative neural network is a hierarchical structure that corresponds to the primary sensory area, the primary sensory Union and the advanced United region according to its function. The primary sensory area is responsible for dealing with some fragmentary feelings, such as color, shape, and syllable. The primary sensory association area connects the fragmented sensation in the primary sensory area to form the concept of representing a single object, such as the concept of visual entity, auditory concept and taste entity concept. The high level united region connects different primary sensory associations, such as audio-visual sensation, and the union of visual taste, that is, the region performs synaesthesia. The cognitive cooperative neural network is divided into functional functions of neurons, including characteristic neurons, primary conceptual neurons and joint neurons. Different types of neurons have different behavioral patterns. Cognitive evolutionary neural networks can quickly form new memories by establishing synaptic connections between neurons. The unconsciousness and introspection mechanism are used to ensure the consistency of the network structure and the external data structure. The model can be applied to the fields of concept acquisition, information fusion, online learning system, robot system and so on. (2) showed that in [87] experiment, cDNA gene knock in mice showed long wavelength perception enhancement and obtain new color discrimination ability. The experiment suggests that the perceptual system of the organism or the structure of the nervous system can be expanded artificially, such as the use of genetic engineering in [87]. Inspired by the above, this paper puts forward the following question: can we develop an intelligent agent that can expand the perception ability online, thereby breaking the perception limit of the intelligent subject. To solve this problem, we propose a perceptive evolutionary neural network, including type I, new sensory receptors, adding existing senses and types of II, and new senses emerging into agents. When new sensors join the existing senses when new receptors receive stimulation with existing receptor for the stimulation of afferent to the primary sensory areas, characteristics of neurons in this area from the feature extraction and the inherent feeling is extracted from the new sensor characteristics are combined, formed from the concept of deepen. By establishing synapses between the characteristic neurons and the new-type receptors, the response dimensions of the characteristic neurons are extended online. When the new sensory organ emerges in the intelligent body, the stimulation received by the new sensory receptor is introduced into the primary sensory area with the stimulus received by the sensorimotor, and processed into fragmented sensation in this area. These fragmentary sensations are transmitted upwards along the network structure to the primary sensory Union and activate the conceptual neurons in response in the region. Then, the concept neuron will activate the signal transduction to the advanced joint area, and the new sense organ and the existing sense will connect with the combined neuron in this area, so as to form new sensory and inherent sensory cooperation. From the point of view of the calculation, the model answers part of the [87] article about "..." Create additional types of sensory neurons or promote the emergence of neural circuits to compare the problems of new and existing sensory responses. The cognitive evolutionary neural network can be applied to information fusion, online learning system, robot system and other fields. (3) a variety of neurophysiological experiments [142146187] and medical cases show that the cerebral cortex and biological receptors are extensible. Based on perceptive cooperative neural network, perceptive evolutionary neural network, and these neurophysiological experiments and medical cases, the theory of cortical receptor artificial expansion is proposed in this paper. Based on this theory, the concept of artificial evolution is proposed, that is, artificial evolution aims to achieve evolution at the life level through the reorganization and expansion of the senses - the brain. Although the concept and theory are at the tentative stage at present, the concept and theory are very good to be excavated and have good inspiration. Cognitive cooperative neural networks and perceptual evolutionary neural networks are designed to simulate the perception, collaboration and evolutionary behavior of organisms. The validity of the two models is preliminarily verified in the experiment. However, there is a long way to go to put these two models into practical applications. The latter part of the thesis discusses some problems, mainly focusing on how the microscopic physiological structure and physiological processes relate to the macro intelligent behavior. Although the discussion of these problems is relatively rough, these are all problems worth thinking deeply. It is hoped that these problems can be further theorized and engineered.
【學(xué)位授予單位】：南京大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP18
，

本文編號(hào)：1343047