(3.210.184.142) 您好!臺灣時間:2021/05/09 10:04
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

: 
twitterline
研究生:林侑賢
研究生(外文):Yo-Hsien Lin
論文名稱:可演化學習的多層類分子神經系統之數位電路建構
論文名稱(外文):An Implementation of An Evolvable Multilevel Neuromolecular System on Digital Circuits
指導教授:陳重臣陳重臣引用關係
指導教授(外文):Jong-Chen Chen
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:資訊管理系碩士班
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2003
畢業學年度:91
語文別:中文
論文頁數:111
中文關鍵詞:演化式適應性人工式大腦多層演化式學習演化式硬體數位晶片
外文關鍵詞:evolvable hardwarechipsmultilevel evolutionary learningartificial brainevolutionary adaptability
相關次數:
  • 被引用被引用:6
  • 點閱點閱:93
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:15
  • 收藏至我的研究室書目清單書目收藏:0
人類大腦是一個高度活動與非同步協調的網路,它具有強大的資訊處理能力,讓我們可以思考、幻想、作夢等。類分子神經系統(Artificial NeuroMolecular System,ANM系統)是一個動機於大腦資訊處理的系統能夠自我組織學習。目前ANM系統已經證實在機器人迷宮導航、圖形辨識、中文字辨識與B型肝炎判斷等都具有很好的成果。至現在為止,ANM系統都是以電腦模擬的方式來實作,這種方式需要相當大的計算資源,因此這個研究的目的將以數位電路來實作ANM系統,使它具備即時處理的基礎,並且可為新興的分子、類分子神經電子技術提供一個架構範本。
本研究即根據ANM系統的運作原理提出其硬體架構概念,並透過電路設計與模擬軟體完成電路規劃與連結。研究中設計兩個實驗來測試此一系統。根據實驗結果顯示,此系統擁有很好的學習能力,它也證實系統能夠自我組織學習,即系統會依據不同的模式(patterns)選擇有意義的位元(bits),這些位元可容忍雜訊的干擾。最後,系統證明其擁有很好的容錯能力去處理空間與時間的干擾。
A biologically inspired neuromolecular architecture implemented on digital circuits is proposed in this study. Our brain is a highly activated, asynchronous concurrent network. This network has significant information processing capability that allows us to think, imagine, dream, and so on. Artificial neuromolecular system (ANM) is a computer simulation model motivated from human brain information processing. Self-organizing learning is the essence of the model. The system was applied to a number of problem domains and demonstrated satisfactory results, including robot navigation, pattern recognition, Chinese character recognition, and hepatitis-B differentiation. Previously, the model was implemented by computer simulation model. It requires significant computational power to perform simulation. The implementation of this model on digital circuits would allow it to perform on a real-time basis and to provide an architectural paradigm for emerging molecular or neuromolecular electronic technologies.
Two experiments ware performed. The experiment result showed that the system has good learning capability. It also demonstrated that the system can select significant bits to different to patterns and in significant bits allow noise tolerance. Finally, the system demonstrated good tolerance capability in dealing with noises in space and time.
摘 要 i
ABSTRACT ii
誌 謝 iii
目 錄 iv
圖目錄 vi
表目錄 viii
一、 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 研究流程 2
1.4 論文架構 4
二、 文獻探討 5
2.1 類神經網路(Artificial Neural Networks,ANN) 5
2.2 基因演算法(Genetic Algorithms,GAs) 6
2.3 演化式硬體(Evolvable Hardware,EHW) 8
2.3.1 演化式硬體的基本觀念 8
2.3.2 演化的種類 9
2.3.3 演化式硬體評估 10
2.4 ANM系統(Artificial NeuroMolecular System) 11
三、 研究架構 17
3.1 細胞骨架的資訊處理(Cytoskeletal Dynamics) 17
3.2 多層演化式學習(Multilevel Evolutionary Learning) 20
3.3 細胞骨架的電路架構 21
3.4 基礎設計原理 23
3.4.1 細胞骨架的環繞排列方式(wrap-around fashion) 23
3.4.2 PU的視野 24
3.4.3 相鄰PU的連接方式 24
3.4.4 組成分子的設計原理 26
3.4.5 讀入酵素的設計原理 26
3.4.6 讀出酵素的設計原理 27
3.4.7 訊號延遲的設計原理 27
3.4.8 訊號中斷的設計原理 28
3.5 電路架構細部概念 29
3.5.1 連接輸入部門(connection input dept.) 29
3.5.2 中斷部門(interrupt dept.) 30
3.5.3 整合部門(integration dept.) 31
3.5.4 延遲輸出部門(delay output dept.) 32
3.6 PU電路圖與初步模擬結果 33
3.7 完整的數位式資訊處理神經元電路圖 38
3.8 關於DCN電路的編譯(Compilation) 39
3.9 定義DCN執行時間 41
3.10 關於DCN電路的模擬(Simulation) 42
3.11 演化學習規則 45
3.12 關於實驗誤差值的計算 47
四、實驗設計與結果 48
4.1 實驗架構 48
4.2 實驗說明 49
4.3 實驗壹:四組圖形學習 50
4.3.1 適應值計算 51
4.3.2 實驗壹訓練結果 52
4.4 實驗貳:四十組圖形學習 55
4.4.1 實驗貳訓練結果 59
4.4.2 實驗貳測試實驗 60
4.4.3 實驗貳測試結果 64
五、結論與建議 78
5.1 未來研究與建議 79
參考文獻 80
附錄A PU各元件細部電路圖與真值表 83
1.H.J. Bremermann, Optimization through evolution and recombination, in: M.C. Yovits, G.T. Jacobi and G.D. Goldstein, eds., Self-Organizing Systems (Spartan Books, Washington, D.C., 1962) 93-106.
2.J.-C. Chen, Computer experiment on evolutionary learning in a multilevel neuromolecular architecture, Ph.D. Dissertation, Department of Computer Science, Wayne State University, Detroit, U.S.A., 1993.
3.J.-C. Chen and M. Conrad, Learning Synergy in a Multilevel Neuronal Architecture, BioSystem, Vol.32 (1994a) 111-142.
4.J.-C. Chen and M. Conrad, A Multilevel Neuromolecular Bypass Principle to Facilitate Evolutionary Learning, Physica D, Vol.75 (1994b) 417-437.
5.J.-C. Chen, 1998, Problem Solving with a Perpetual Evolutionary Learning Architecture, Applied Intelligence (1998) 53-71.
6.J.-C. Chen, Toward an Evolvable Neuromolecular Hardware: Realization of A Multilevel Brain-Like Architecture with Digital Circuits, NeuroComputing (2001). (accepted)
7.M. Conrad, 1974, Evolutionary learning circuits, J. Theor. Biol. 46 (1974) 67-188.
8.M. Conrad, Molecular information structures in the brain, J. Neurosci. Res. 2 (1976a) 233-254.
9.M. Conrad, Complementary molecular models of learning and memory, BioSystems 8 (1976b) 119-138.
10.M. Conrad, R.R. Kampfner, and K.G. Kirby, Neuronal dynamics and evolutionary learning, in: M. Kochen and H. Hastings, eds., Advances in Cognitive Science: Steps Toward Convergence 104 (Westview Press, Boulder, CO, 1988) 169-189.
11.M. Conrad, The brain-machine disanalogy, BioSystems 22 (1989) 197-213.
12.M. Conrad, Electronic instabilities in biological information processing, in: P.I. Lazarev, ed., Molecular Electronics (Kluwer Academic Publishers, Amsterdam, 1991) 41-50.
13.L. Fogel, A. Owens, and M. Walsh, Artificial Intelligence through Simulated Evolution (Wiley, New York, 1966).
14.A.S. Fraser, Simulation of genetic systems by automatic digital computers, Australian J. of Biol. Sci. 10 (1957) 484-491.

15.P. Greengard, Phosphorylated proteins as physiological effectors, Science 199 (1978) 146-152.
16.L.M. Griffith and T.D. Pollard, The interaction of actin filaments with microtubules and microtubule-associated proteins, J. Biol. Chem. 257 (1982) 9143-9151.
17.S. Grossberg, Nonlinear neural networks: principles, mechanisms, and architectures. Neural Networks (1988) 1:17-61.
18.Gunnar Tufte, Prototyping a GA Pipeline for Complete Hardware Evolution, EH'99 (1999) 143-150.
19.S.R. Hameroff and R.C. Watt, Information processing in microtubules, Journal of Theoretical Biology (1982) 549-561.
20.S.R. Hameroff, Ultimate Computing (North-Holland, Amsterdam, 1987).
21.S.R. Hameroff, J.E. Dayhoff, R. Lahoz-Beltra, A. Samsonovich, and S. Rasmussen, Conformational automata in the cytoskeleton: models for molecular computation, Computer 25, 11 (1992) 30-39.
22.D.O. Hebb, The first stage of perception: growth of the assembly, The Organization of Behavior (1949) 60-78.
23.T. Higuchi, M. Murakawa, M. Iwata, I. Kajitani, W. Liu, and M. Salami, Evolvable Hardware at Function Level, Proc. 1997 IEEE Int. Conf. on Evolutionary Computation (ICEC97) (1997) 187-192.
24.J. Holland, Adaptation in Natural and Artificial Systems.(University of Michigan Press, Ann Arbor, MI.,1975)
25.I. Kajitani, M. Murakawa, D. Nishikawa, H. Yokoi, N. Kajihara, M. Iwata, D. Keymeulen, H. Sakanashi and T. Higuchi Proc, An Evolvable Hardware Chip for Prosthetic Hand Controller, Bio-Inspired Systems (MicroNeuro99) (1999) 179-186.
26.F.H. Kirkpatrick, New models of cellular control: membrane cytoskeletons, membrane curvature potential, and possible interactions, BioSystems 11 (1979) 85-92.
27.E.A. Liberman, S.V. Minina, and K.V. Golubtsov, The study of the metabolic synapse II: comparison of cyclic 3',5'-AMP and cyclic 3',5'-GMP effects, Biophysics 22 (1975) 75-81.
28.E.A. Liberman, S.V. Minina, N.E. Shklovsky-Kordy, and M. Conrad, Microinjection of cyclic nucleotides provides evidence for a diffusional mechanism of intraneuronal control, BioSystems 15 (1982a) 127-132.

29.E.A. Liberman, S.V. Minina, N.E. Shklovsky-Kordy, and M. Conrad, Change of mechanical parameters as a possible means for information processing by the neuron (in Russian), Biophysics 27 (1982b) 863-870.
30.G. Matsumoto, S. Tsukita, and T. Arai, Organization of the axonal cytoskeleton: differentiation of the microtubule and actin filament arrays, in: F.D. Warner and J.R. McIntosh, eds., Kinesin, Dynein, Cell Movement, Microtubule Dynamics (Alan R. Liss, New York) (1989) 335-356.
31.Nicholas J. Macias, Ring Around the PIG: A Parallel GA with Only Local Interactions Coupled with a Self-Reconfigurable Hardware Platform to Implement an O(1) Evolutionary Cycle for Evolvable Hardware, IEEE, Proceedings of the 1999 Congress on Evolutionary Computation (1999) 1067 ~ 1075.
32.T.D. Pollard, S.C. Selden, and P. Maupin, Interaction of actin filaments with microtubules, J. Cell Biol. 99 (1984) 33-37.
33.I. Rechenberg, Evolutionsstrategie: Optimierung Technischer Systeme nach Prinzipien der Biologischen Evolution (Frommann-Holzboog, Stuttgart, Germany, 1973).
34.M. Salami, H. Sakanashi, M. Tanaka, M. Iwata, and T. Higuchi, On-Line Compression of High Precision Printer Images by Evolvable Hardware, DCC '98 Data Compression Conference, IEEE Computer Society Press (1998) 219-228.
35.H.P. Schwefel, Numerical Optimization of Computer Models (Wiley, Chichester, 1981)
36.R.B. Vallee, G.S. Bloom, and W.E. Theurkauf, Microtubule-associated proteins: subunits of the cytomatrix, J. Cell Biol. 99 (1984) 38-44.
37.P. Werbos, Beyond regression: new tools for prediction and analysis in the behavioral sciences, Ph.D. Thesis, Harvard University (1974).
38.P. Werbos, Backpropagation and neurocontrol: a review and prospectus, in: Proc. Int. Joint Conf. Neural Networks (1989) 209-216.
39.P. Werbos, The Cytoskeleton: Why It May Be Crucial to Human Learning and to Neurocontrol, Nanobiology, Vol. 1 (1992) 75-95.
40.X. Yao, Following the path of evolvable hardware, Commun. ACM 42, 4 (1999) 47-49.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊
 
系統版面圖檔 系統版面圖檔