請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66650完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 劉長遠(Cheng-Yuan Liou) | |
| dc.contributor.author | Pei-Hsun Hsu | en |
| dc.contributor.author | 許珮薰 | zh_TW |
| dc.date.accessioned | 2021-06-17T00:48:53Z | - |
| dc.date.available | 2013-12-28 | |
| dc.date.copyright | 2011-12-28 | |
| dc.date.issued | 2011 | |
| dc.date.submitted | 2011-12-08 | |
| dc.identifier.citation | [1] J. J. Hopfield, Search for memories, Sudoku, implicit check-bits, and the iterative use of not-always-correct rapid neural computation, Neural Computation 20 (5) (2008) 1119-1164.
[2] E. Gardner, The space of interactions in neural network models, J. Phys. A: Math. Gen. 21 (1988) 257-270. [3] B. Muller and J. Reinhardt, Neural networks: An Introduction, Springer-Verlag, 1990. [4] J. J. Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proc. Natl. Acad. Sci. USA 79 (8) (1982) 2554-2558. [5] A. B. Kaufman, An expandable ferroelectic random access memory, IEEE Transactions on Computers c-22 (2) (1973) 154-158. [6] L. F. Lemmens, J. D. Sitter and J. T. Devreese, Ground-state theorem for free polarons, Phys. Rev. B8 (1973) 2717-2720. [7] D. J. Thouless, et al., Solution of “solvable model of a spin glass”, Phil. Mag. 35 (3) (1977) 593-601. [8] D. J. Gross and M. Mezard, The simplest spin glass, Nucl. Phys. FSB 240 (1984) 431-452. [9] D. O. Hebb, The Organization of Behavior, Wiley, New York, 1949. [10] G. E. Hearn, Y. Zhang and P. Sen, Comparison of SISO and SIMO neural control strategies for ship track keeping, IEE Proceedings-control Theory and Applications 144 (2) (1997) 153-165. [11] M. E. Salgado and A. Conley, MIMO interaction measure and controller structure selection, Int. J. Control 77 (4) (2004) 367-383. [12] J.M. Wu, Natural discriminant analysis using interactive Potts models, Neural Computation 14 (3) (2002) 689-713. [13] W. Kautz and R. Singleton, Nonrandom binary superimposed codes, IEEE Transactions on Information Theory 10 (4) (1964) 363-377. [14] J. Kiefer and H. P. Wynn, Optimum balanced block and Latin square designs for correlated observations, The annals of Statistics 9 (4) (1981) 737-757. [15] J.P. Delahaye, The science behind Sudoku, Sci Am. 294 (6) (2006) 80-87. [16] E. R. Kandel, J. H. Schwartz and T. M. Jessell, Principles of Neural Science, McGraw-Hill Medical, New York, 2000. [17] M. A. Coway, et al., The formation of flashbulb memories, Memory & Cognition 22 (3) (1994) 326-343. [18] D. L. Schacter, Searching for Memory: The Brain, the Mind, and the Past, Basic Books, 1996. [19] S. Qin, et al., Dissecting medial temporal lobe contributions to item and associative memory formation, NeuroImage 46 (2009) 874-881. [20] I. Tendolkar, et al., Probing the neural correlates of associative memory formation: a parametrically analyzed event-related functional MRI study, Brain Research 1142 (2007) 159-168. [21] A. M. Achim, et al., Medial temporal lobe activations during associative memory encoding for arbitrary and semantically related object pairs, Brain Research 1161 (2007) 46-55. [22] F. Rosenblatt, Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms, Spartan Books, Washington DC, 1962. [23] B. Widrow, 30 years of adaptive neural networks: perceptron, madaline, and backpropagation, Proceedings of the IEEE 78 (9) (1990) 1415-1442 . [24] B. Widrow, et al., Generalization and information storage in networks of adaline neuron in self-organizing systems, Self Organizing Systems 435–-461, Spartan Books, Washington DC, 1962. [25] F. Rosenblatt, The perceptron: a probabilistic model for information storage and organization in the brain, Cornell Aeronautical Laboratory, Psychological Review v65 (6) (1958) 386-–408. [26] P. Dayan and L. F. Abbott, Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems, MIT Press, Cambridge, 2001. [27] E. N. Petropoulou, A discrete equivalent of the logistic equation, Advances in Difference Equations 2010 (2010) 457073. [28] J.M. Wu, Z.H. Lin and P.H. Hsu, Function approximation using generalized adalines, IEEE Transactions on Neural Networks 17 (3) (2006) 541-558. [29] J.M. Wu, Multilayer Potts perceptrons with Levenberg-Marquardt learning, IEEE Transactions on Neural Networks 19 (12) (2008) 2032-2043. [30] J.M. Wu, and S.J. Chiu, Independent component analysis using Potts models, IEEE Transactions on Neural Networks 12 (2) (2001) 202-211. [31] J.M. Wu and Z.H. Lin, Learning generative models of natural images, Neural Networks 15 (3) (2002) 337-347. [32] B. Hayes, Unwed numbers: the mathematics of Sudoku, a puzzle that boasts “no math required!”, Amer. Scientist 94 (12) (2006). [33] A. F. Gabor and G. J. Woeginger, How *not* to solve a Sudoku, Operations Research Letters 38 (6) (2010) 582-584. [34] P. Babu, et al., Linear systems, sparse solutions, and Sudoku, IEEE Signal Processing Letters 17 (1) (2010) 40-42. [35] T. K. Moon, J. H. Gunther and J. J. Kupin, Sinkhorn solves Sudoku, IEEE Transactions on Information Theory 55 (4) (2009). [36] Y. Erlich, et al, DNA Sudoku— harnessing high-throughput sequencing for multiplexed specimen analysis, Genome research 19 (7) (2009) 1243-1253. [37] G. Dahl, Permutation matrices related to Sudoku, Linear Algebra and its applications 430 (8-9) (2009) 2457-2463. [38] D. W. Tank and J. J. Hopfield, Simple optimization networks: an A/D converter and a linear programming circuit, IEEE Circuits and Systems CAS-33 (1986) 533-541. [39] J. Hertz , A. Krogh and R. G. Palmer, Introduction to the Theory of Neural Computation, Addison-Wesley, 1991. [40] J. J. Hopfield, Neurons with graded response have collective computational properties like those of 2-state neurons, Proc. Natl. Acad. Sci. USA 81 (10) (1984) 3088-3092. [41] A. G. Hanlon, Content-addressable and associative memory systems— a survey, IEEE Transactions on Electronic Computers EC-15 (4) (1966) 509-521. [42] B. Kosko, Bidirectional associative memories, IEEE Transactions on Systems, Man, and Cybernetics 18 (1) (1988) 49-60. [43] Y. Park, Optimal and robust design of brain-state-in-a-box neural associative memories, Neural Networks 23 (2010) 210-218. [44] M. H. Hassoun, Associative Neural Memories: Theory and Implementation, Oxford University Press, New York, 1993. [45] A. N. Michel, J. A. Farrell and H. F. Sun, Analysis and synthesis techniques for Hopfield type synchronous discrete time neural networks with application to associative memory, IEEE Transactions on Circuits and Systems 37 (11) (1990) 1356–-1366. [46] K. Andrews, et al., The development of Turbo and LDPC codes for deep-space applications, Proceedings of the IEEE 95 (11) (2007) 2142-2156. [47] W. Huffman and V. Pless, Fundamentals of Error-correcting Codes, Cambridge University Press, 2003. [48] Website. [Online]. Available: http://www.websudoku.com/ [49] F. T. Sommer and T. Wennekers, Associative memory in networks of spiking neurons, Neural Networks 14 (6-7) (2001) 825-834. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/66650 | - |
| dc.description.abstract | 本文探討利用二態神經元設計嵌入檢查規則的資料模式編碼，建構一個具有資訊回復、容錯編碼和聯想式記憶特性的類神經系統。
首先引用兩個微分方程式描述二態神經元的內場與活化，且利用模擬正規化的連結方式，將傳統多個二態神經元間獨立的活化狀態改造為可用來表示多態的artificial Potts neuron。利用提出的inhibitory connection方式，可將多個artificial Potts neuron組織出cell、connected cell以及connected cubical cell，實現二元Latin square編碼、K字元Latin square編碼以及Sudoku編碼。嵌入檢查規則的Sudoku編碼具有自動偵測錯誤與修復錯誤的能力。網路的收斂則使用Kullback-Leibler divergence的最小化機制，有助於找到系統組態的最佳解，也是對應到提供部分提示的Sudoku解答。 藉由應用Hebb’s rule，使提出的類神經系統具備聯想式記憶的功能。記憶多組完整Sudoku之後，將原本提供的32％內容提示降至13％，仍可找出記憶中的Sudoku解答。透過Sudoku在空間上特殊的結構性質，可將多個Sudoku以重疊相同內容的組織方法，建構出可以編寫更複雜資訊的compound pattern。實驗結果驗證compound pattern的設計與再生的可行性，以及可應用在模擬基因與人腦的關聯記憶。 | zh_TW |
| dc.description.abstract | This work explores bipolar neural circuits for constructing a neural system with check-rule embedded pattern restoration, fault-tolerant information encoding and associative memory. A bipolar neural unit is extended with an internal field and an activation, respectively characterized by exponential growth and logistic differential equations, in response to an external field that summarizes inhibitory and excitatory stimuli. On the basis, multiple bipoar neural units are coupled to organize an artificial multi-state Potts neuron, and multiple artificial Potts neurons are interconnected for binary Latin square encoding, K-alphabet Latin square encoding and Sudoku encoding. Check-rule embedded Sudoku patterns are self-correctable for automatic information restoration subject to partial clues. Interactive dynamics of organized bipolar neural units operate in consistent with annealed Kullback-Leibler (KL) divergence minimization, which pursues network relaxation to ground states.
By Hebb's rule, the neural system acquires capability of memorizing Sudoku patterns and it has shown great performance in restoring memorized Sudoku puzzles of any level and reducing partial clues from 32% to 13% of the content. Compound Sudoku patterns which encode complex information in the spatial composition are constructed by overlaying common subgrids of multiple Sudoku patterns. Design and regeneration of compound Sudoku patterns in different forms have been experimented and further applied for simulating functionalities of gene and associative memory in human brain. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T00:48:53Z (GMT). No. of bitstreams: 1 ntu-100-D94922007-1.pdf: 1673336 bytes, checksum: e989aec307cec395e15d5618173049c7 (MD5) Previous issue date: 2011 | en |
| dc.description.tableofcontents | I. Introduction……………………………………………………………………... 1
II. Neural organizations……………………………………………………………. 9 A. Exponential growth and logistic differential equations……………………… 9 B. Coupling bipolar units for Potts encoding………………………………….. 12 C. Interconnected artificial Potts neurons for binary Latin square encoding….. 15 D. K-alphabet Latin square encoding………………………………………….. 17 III. Neural systems of Sudoku pattern restoration………………………………… 20 A. Sudoku encoding……………………………………………………...…….. 20 B. Mathematical frameworks…………………………………………………... 25 C. Annealed Kullback-Leibler divergence minimization………...……………. 27 IV. Sudoku associative memory……………...……………………………………. 30 A. Hebb's rule……………...……………...……………………………………. 30 B. Comparison between Sudoku associative memory and random access memory.…...……………...……………...…………………………………………. 36 V. Quantitative performance evaluation…………………….……………………. 37 A. Sudoku puzzle resolution…………………….…………………..…………. 37 B. Sudoku associative memory…………………….………………..…………. 39 1. Pattern restoration…………………….………………………………. 39 2. Fewer clues…………………….………………………..……………. 42 3. Condense clues………………….………………..……..……………. 44 4. Error correction…………….………………..…………..……………. 47 5. Memory capacity…………….………………..……..……….………. 48 VI. Design and regeneration of compound Sudoku patterns……..……….………. 49 VII.Sudoku genes……..……….……….………………………………...……….. 53 A. Information compression of Sudoku genes……………………...…………. 53 B. Parallel and distributed repairing of incomplete Sudoku genes...…….….…58 VIII. Sudoku associative memory in human brain...………………………...……. 61 A. Memory formation...……………………………………...…………...……. 61 B. Memory retrieval and association………………………...…………...……. 63 IX. Conclusions...……………………...…………...…………………………...…. 71 Reference………………………...…………………………………………...……. 75 | |
| dc.language.iso | en | |
| dc.subject | Sudoku | zh_TW |
| dc.subject | associative memory | zh_TW |
| dc.subject | self-correction neural encoding | zh_TW |
| dc.subject | mean field annealing | zh_TW |
| dc.subject | Hopfield neural networks | zh_TW |
| dc.subject | pattern restoration | zh_TW |
| dc.subject | memory dependent computing | zh_TW |
| dc.title | Sudoku 聯想記憶 | zh_TW |
| dc.title | Sudoku Associative Memory | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 100-1 | |
| dc.description.degree | 博士 | |
| dc.contributor.coadvisor | 吳建銘(Jiann-Ming Wu) | |
| dc.contributor.oralexamcommittee | 趙坤茂(Kun-Mao Chao),林智仁(Chih-Jen Lin),林軒田(Hsuan-Tien Lin),呂育道(Yuh-Dauh Lyuu) | |
| dc.subject.keyword | Sudoku,associative memory,self-correction neural encoding,mean field annealing,Hopfield neural networks,pattern restoration,memory dependent computing, | zh_TW |
| dc.relation.page | 80 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2011-12-08 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-100-1.pdf 未授權公開取用 | 1.63 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。