本文關鍵詞：視覺印象深度學習算法研究　出處：《蘇州大學》2016年博士論文　論文類型：學位論文

  更多相關文章： 李群視覺印象 李群深度學習 李群神經(jīng)網(wǎng)絡 李群自動編碼器

【摘要】：視覺印象是儲存在人們記憶中的視覺信息,它是視覺認知過程中的一種重要形式。人類通過視覺獲得的感官刺激,經(jīng)由大腦的信息處理之后,形成有關認知客體的形象。這個形象以記憶的形式儲存在腦海中,構(gòu)成能夠幫助人類理解與認知的視覺印象。視覺印象是人類大腦能夠準確高效地完成各種各樣復雜任務的基礎。大腦在大部分時候直接借助于記憶中的視覺印象幫助視覺信息的處理,而不是通過盲目地計算。由于人類在認知客觀事物時,八成以上的信息都來源于視覺并且在進行目標識別等任務中,人們總是通過已有的視覺印象去認知當前的事物,因此研究視覺印象機制對于模式識別、計算機視覺等領域具有重要的作用。深度學習通過堆疊單層模塊構(gòu)建一種深層的非線性網(wǎng)絡,能夠?qū)崿F(xiàn)對復雜函數(shù)的無限逼近。深度學習能夠以非監(jiān)督的形式逐漸學習出不同抽象級別的特征,提供一種更具表現(xiàn)力的分布式表示方式。由于其自動學習特征的特性,使得相對于傳統(tǒng)特征選擇方法來說,深度學習節(jié)省了人工設計特征的代價。深度學習高度有效的特征提取方式,使其在目標識別等領域的應用都帶來了突破性的結(jié)果。人類視覺皮層具有一個深度的結(jié)構(gòu)。從模擬生物機制的角度,這成為支持深度學習技術(shù)的一個強有力的證據(jù)。從某種程度上,深度學習對人類逐層進行的認知過程進行了模擬。人腦的深度結(jié)構(gòu)決定了視覺印象是對視覺信息逐步抽象的過程。這意味著逐層抽象的視覺印象能夠與深度學習逐層提取的隱藏特征相對應。因而,將視覺印象機制與深度學習技術(shù)相結(jié)合是十分有潛力的研究方向。如何利用深度學習方法模擬人類視覺認知過程中產(chǎn)生的視覺印象是一個亟待解決的問題。這個問題要求設計的深度學習算法一方面要能夠體現(xiàn)視覺印象的一些特點,另一方面也要能夠完成視覺印象的相關功能。在深度學習的基礎上,如何能夠有效地提取出具有層次結(jié)構(gòu)的視覺印象以及如何保證獲得的視覺印象對微小擾動的魯棒性,都是在設計深度學習算法時需要面臨的主要問題。視覺印象深度問題是深度學習的核心問題之一,本文針對視覺印象深度問題的層次特征和穩(wěn)定特征等方面進行研究,取得的成績主要包括:第一,本文在視覺印象的基礎上,提出了兩種視覺印象模型:再認模型和泛化模型用來模擬人類視覺系統(tǒng)的認知過程。本文給出利用一個深度神經(jīng)網(wǎng)絡學習到的視覺印象如何能夠被有效地遷移到其他視覺認知任務中。通過復用以非監(jiān)督的方式訓練得到的隱藏層,提出的算法能夠在目標任務中大幅度地減少需要被標注圖像樣本的數(shù)量。實驗證實了在源任務中估計的參數(shù)的確能夠幫助網(wǎng)絡在目標任務中提高目標分類的結(jié)果。第二,本文利用視覺印象給出一個用于訓練拓撲深度神經(jīng)網(wǎng)絡的全新的方法。通過結(jié)合降噪自動編碼器以及帶有Hessian正則化項的收縮自動編碼器,能夠獲得一個對輸入數(shù)據(jù)的小幅度變化十分魯棒的自動編碼器。利用切傳播算法來展示本文提出的方法如何能夠捕獲視覺印象的流形結(jié)構(gòu)并且建立一個拓撲圖冊的圖集。然后,利用學習到的特征去初始化一個深度網(wǎng)絡,使用相對于其他模型更小的參數(shù)集合獲得了更好的分類結(jié)果。第三,給出了本文開發(fā)的一個捕獲視覺印象李群流形結(jié)構(gòu)的新算法。通過設計單層李群模型,驗證該表示學習算法如何能夠被堆疊出一個深層的架構(gòu)。另外,本文還設計了一個基于李群的梯度下降算法來解決神經(jīng)網(wǎng)絡權(quán)重的學習問題。實驗結(jié)果表明本文提出的方法能夠獲得更加適用于深度網(wǎng)絡的特征并且該特征的計算是十分有效的。綜上所述,本文的創(chuàng)新點包括:(1)提出了李群視覺印象深度學習的表示新方法。(2)提出了視覺印象深度學習的度量方法,包括視覺印象深度學習的層次度量、拓撲度量和李群度量。(3)提出了視覺印象深度學習新算法。
[Abstract]:Visual impression is the visual information stored in people's memory. It is an important form of visual cognition. Human sensory stimuli obtained through the vision form the image of the cognitive object after the information processing of the brain. This image is stored in the form of memory in the mind, forming a visual impression that can help human understanding and cognition. Visual impression is the basis for the human brain to accomplish a variety of complex tasks accurately and efficiently. The brain helps the processing of visual information directly by means of the visual impression in memory, rather than by blind calculation. Because of human's cognition of the objective things, more than 80% of the information from the visual and object recognition tasks, people always through the visual impression to the cognition of things, so the study of the visual impression mechanism plays an important role in the field of pattern recognition, computer vision etc.. Deep learning constructs a deep nonlinear network by stacking a single layer module, which can achieve infinite approximation to complex functions. Deep learning can gradually learn the characteristics of different levels of abstraction in an unsupervised form, and provide a more expressive distributed representation. Because of the characteristics of its automatic learning features, it saves the cost of artificial design features compared to the traditional feature selection method. Deep learning is a highly effective feature extraction method, making it a breakthrough in the application of target recognition and other fields. The human visual cortex has a deep structure. From the point of view of the mimic biological mechanism, this has become a strong evidence to support deep learning technology. In a way, deep learning has simulated the cognitive process of human being. The depth structure of the human brain determines the visual impression is the process of the gradual abstraction of the visual information. This means that the visual impression of layer by level abstraction corresponds to the hidden feature extracted by layer by layer. Therefore, the combination of visual impression mechanism and deep learning technology is a potential research direction. How to use the depth learning method to simulate the visual impression produced in the process of human visual cognition is an urgent problem to be solved. This problem requires that the deep learning algorithm designed should embody some characteristics of visual impression, and on the other hand, it can complete the related functions of visual impression. On the basis of deep learning, how to effectively extract hierarchical visual impression and how to ensure the visual impression to gain the robustness of small perturbations are the main problems that need to be faced when designing deep learning algorithm. The visual impression of depth is one of the most important problems of deep learning, aiming at the problem of the visual impression of depth level features and stable characteristics, the main achievements include: first, based on the visual impression, puts forward two kinds of visual impression model: the recognition model and generalization model is used to simulate the process of human cognition the visual system. This paper presents how the visual impression learned by a deep neural network can be effectively migrated to other visual cognitive tasks. By reusing the hidden layer trained in an unsupervised way, the proposed algorithm can significantly reduce the number of image samples needed to be tagged in the target task. The experiment confirms that the estimated parameters in the source task do help the network to improve the result of the target classification in the target task. Second, this paper uses visual impression to give a new method for training topology depth neural network. By combining the noise reduction automatic encoder and the shrinking auto encoder with Hessian regularization term, we can get an automatic encoder which is robust to small changes in input data. The method of cutting propagation is used to show how the method proposed in this paper can capture the manifold structure of visual impression and set up an atlas of a topologic atlas. Then, using the learned features to initialize a depth network, the better classification results are obtained by using a smaller set of parameters relative to the other models. Third, a new algorithm for capturing the Li Qun manifold structure of visual impression is developed in this paper. By designing a monolayer Li Qun model, it is verified how the learning algorithm can be stacked out of a deep architecture. In addition, this paper also designs a gradient descent algorithm based on Li Qun to solve the learning problem of neural network weight. The experimental results show that the proposed method can be more suitable for the characteristics of the depth network and the computation of this feature is very effective. To sum up, the innovative points of this paper include: (1) a new method of expressing Li Qun's visual impression deep learning is proposed. (2) a measure of the depth learning of visual impression is proposed, including the hierarchical measurement, topological metric and Li Qun measure of the depth learning of visual impression. (3) a new algorithm for visual impression depth learning is proposed.
【學位授予單位】：蘇州大學
【學位級別】：博士
【學位授予年份】：2016
【分類號】：TP391.41;TP181

【相似文獻】

相關期刊論文 前1條

1 ;潮流新品[J];中國新聞周刊;2013年29期

相關重要報紙文章 前1條

1 子今;第一視覺印象[N];經(jīng)濟參考報;2004年

相關博士學位論文 前1條

1 楊夢鐸;視覺印象深度學習算法研究[D];蘇州大學;2016年

，

本文編號：1340158