學術產出-Theses
Article View/Open
Publication Export
-
題名 倒傳導神經網路的有效性、使用性與顯著性之研究
The Study of Validity, Utilization and Salience of the BP Networks作者 陳怡達
Chen, Yi-Da貢獻者 蔡瑞煌
Ray Tsaih
陳怡達
Chen, Yi-Da關鍵詞 分類學習
倒傳導神經網路
敏感度分析
競爭學習
遮蔽效應
不相關線索的影響
category learning
back propagation neural networks
sensitivity analysis
competitive learning
overshadowing
the deleterious of an irrelevant cue日期 2000 上傳時間 31-Mar-2016 15:43:07 (UTC+8) 摘要 本研究的主要目的是檢視倒傳導神經網路是否具有人類在分類學習上所呈現出來的學習效應 — 競爭學習、遮蔽效應與不相關線索的影響。在實驗中，我們採用兩種倒傳導神經網路，來測試激發函數是否會影響倒傳導神經網路的學習。此兩種倒傳導神經網路分別採用sigmoid激發函數與hyperbolic-tangent激發函數。實驗結果顯示，以sigmoid為激發函數與以hyperbolic-tangent為激發函數的倒傳導神經網路都具有這三個學習效應。還有，以sigmoid為激發函數的倒傳導神經網路所呈現出來的學習效應比以hyperbolic-tangent為激發函數的倒傳導神經網路來得顯著。本研究的次要目的在於瞭解有效性（使用性）與敏感度分析的數值是否有對應關係。實驗結果顯示，線索A與線索B的敏感度分析數值差異可以反映出線索A與線索B的有效性差異。然而，敏感度分析數值卻無法準確地顯示線索的有效性數值。
The main objective of this research is to examine whether back propagation neural networks (BP) have the learning effects found in human category learning — competitive learning, overshadowing and the deleterious of an irrelevant cue. Two kinds of BP, BP with sigmoid activation function and BP with hyperbolic-tangent activation function, are investigated to see if the activation function will make BP behave differently. According to the results of our experiments, these three learning effects are demonstrated both in BP with sigmoid and BP with hyperbolic-tangent, but they seems more significant in BP with sigmoid than in BP with hyperbolic-tangent. The second objective of our research is to see if there is a correspondence between the validity (the utilization) and the value of sensitivity analysis, R. From the results of our experiments, we observe that the difference between values of sensitivity analysis with respect to Cue A and Cue B reflects the difference of the validities between Cue A and Cue B. However, the value of sensitivity analysis does not show exactly what validity a cue is.參考文獻 1. Anderson, J.R., Cognitive Psychology and Its Implications, W.H.Freeman, New York, 1990. 2. Anderson, J.R., Learning and Memory: An Integrated Approach, John Wiley and Sons, New York, 1995. 3. Boden, M.A., Artificial Intelligence in Psychology: Interdisciplinary Essays, The MIT Press, Cambridge, 1989. 4. Davey, G., Animal Learning and Conditioning, The Macmillan Press, London, 1981. 5. Edgell, S.E., ”Configural Information Processing in Two-Cue Probability Learning,” Organizational Behavior and Human Performance, Vol.22, 1978, pp.404-416. 6. Edgell, S.E. and Roe, R.M., “Dimensional Information Facilitates the Utilization of Configural Information: A Test of the Cestellan-Edgell and the Gluck-Bower Models,” Journal of Experimental Psychology: Learning, Memory, and Cognition, Vol.21, 1995, pp.1495-1508. 7. Gagne, R.M., “Memory Structures and Learning Outcomes,” Review of Educational Research, Vol.48, 1978, pp.178-222. 8. Gardner, H., The Mind’s New Science: A History of the Cognitive Revolution, Basic Books, New York, 1985. 9. Gluck, M.A. and Bower, G.H., “From Conditioning to Category Learning: An Adaptive Network Model,” Journal of Experimental Psychology: General, Vol.117, 1988, pp.227-247. 10. Grossberg, S., Neural Networks and Natural Intelligence, The MIT Press, Cambridge, 1988. 11. Kruschke J.K. and Johansen M.K., “A Model of Probabilistic Category Learning,” Journal of Experimental Psychology: Learning, Memory and Cognitive, Vol.25, 1999, pp.1083-1119. 12. Hertz, J., Krogh, A. and Palmer R.G., Introduction to the Theory of Neural Computation, Addison Wesley, New York, 1991. 13. Medin, D.L. and Edelson, S.M., “Problem Structure and the Use of Base-Rate Information from Experience,” Journal of Experimental Psychology: General, Vol.117, pp.68-85. 14. Medin, D.L. and Schaffer, M.M., “Context Theory of Classification Learning,” Psychological Review, Vol.85, 1978, pp.207-238. 15. Morris, R.G.M., Parallel Distributed Processing: Implications for Psychology and Neurobiology, Oxford, New York, 1989. 16. Nosofsky, R.M., “Similarity, Frequency, and Category Representations,”Journal of Experimental Psychology: Learning, Memory, and Cognition, Vol.14, 1988, pp.54-65. 17. Regehr, G. and Brooks, L., “Category Organization in Free Classification: The Organizing Effect of an Array of Stimuli,” Journal of Experimental Psychology: Learning, Memory, and Cognition, Vol.21, 1995, pp.347-363. 18. Rescorla, R.A. and Wagner, A.R., "A theory of Pavlovian Conditioning: Variations in the Effectiveness of Reinforcement and Non-reinforcement," In Black, A.H. and Prokasy, W.F. (Eds.), Classical Conditioning Ⅱ: Current Research and Theory, Appleton Century Crofts, New York, 1972. 19. Rumelhart, D.E., Hinton, G.E. and Williams, R.J., ”Learning Internal Representations by Error Propagation,” In Rumelhart, D.E. and McClelland, J. L. (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol.1, The MIT Press, Cambridge, 1986, pp.318-362. 20. Rumelhart, D.E. and McClelland, J.L. (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol.1, The MIT Press, Cambridge, 1986. 21. Schalkoff, R.J., Artificial Neural Networks, McGraw-Hill, New York, 1997. 22. Smith, J.D., Minda, J.P. and Murry, M.J., Jr., “Straight Talk about Linear Separability,” Journal of Experimental Psychology: Learning, Memory, and Cognition, Vol.23, 1997, pp.659-680. 23. Sutton, R.S. and Barto, A.G., “Toward a Modern Theory of Adaptive Networks: Expectation and Prediction,” Psychological Review, Vol.88, 1981, pp. 135-170. 24. Tsaih, R., “Sensitivity Analysis, Neural Networks, and the Finance,” International Joint Conference on Neural Networks, 1999. 描述 碩士
國立政治大學
資訊管理學系
87356017資料來源 http://thesis.lib.nccu.edu.tw/record/#A2002002097 資料類型 thesis dc.contributor.advisor 蔡瑞煌 zh_TW dc.contributor.advisor Ray Tsaih en_US dc.contributor.author (Authors) 陳怡達 zh_TW dc.contributor.author (Authors) Chen, Yi-Da en_US dc.creator (作者) 陳怡達 zh_TW dc.creator (作者) Chen, Yi-Da en_US dc.date (日期) 2000 en_US dc.date.accessioned 31-Mar-2016 15:43:07 (UTC+8) - dc.date.available 31-Mar-2016 15:43:07 (UTC+8) - dc.date.issued (上傳時間) 31-Mar-2016 15:43:07 (UTC+8) - dc.identifier (Other Identifiers) A2002002097 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/83297 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊管理學系 zh_TW dc.description (描述) 87356017 zh_TW dc.description.abstract (摘要) 本研究的主要目的是檢視倒傳導神經網路是否具有人類在分類學習上所呈現出來的學習效應 — 競爭學習、遮蔽效應與不相關線索的影響。在實驗中，我們採用兩種倒傳導神經網路，來測試激發函數是否會影響倒傳導神經網路的學習。此兩種倒傳導神經網路分別採用sigmoid激發函數與hyperbolic-tangent激發函數。實驗結果顯示，以sigmoid為激發函數與以hyperbolic-tangent為激發函數的倒傳導神經網路都具有這三個學習效應。還有，以sigmoid為激發函數的倒傳導神經網路所呈現出來的學習效應比以hyperbolic-tangent為激發函數的倒傳導神經網路來得顯著。本研究的次要目的在於瞭解有效性（使用性）與敏感度分析的數值是否有對應關係。實驗結果顯示，線索A與線索B的敏感度分析數值差異可以反映出線索A與線索B的有效性差異。然而，敏感度分析數值卻無法準確地顯示線索的有效性數值。 zh_TW dc.description.abstract (摘要) The main objective of this research is to examine whether back propagation neural networks (BP) have the learning effects found in human category learning — competitive learning, overshadowing and the deleterious of an irrelevant cue. Two kinds of BP, BP with sigmoid activation function and BP with hyperbolic-tangent activation function, are investigated to see if the activation function will make BP behave differently. According to the results of our experiments, these three learning effects are demonstrated both in BP with sigmoid and BP with hyperbolic-tangent, but they seems more significant in BP with sigmoid than in BP with hyperbolic-tangent. The second objective of our research is to see if there is a correspondence between the validity (the utilization) and the value of sensitivity analysis, R. From the results of our experiments, we observe that the difference between values of sensitivity analysis with respect to Cue A and Cue B reflects the difference of the validities between Cue A and Cue B. However, the value of sensitivity analysis does not show exactly what validity a cue is. en_US dc.description.tableofcontents 封面頁 證明書 致謝詞 論文摘要 目錄 表目錄 圖目錄 CHAPTER 1 INTRODUCTION CHAPTER 2 LITERATURE REVIEW 2.1 BACK PROPAGATION NEURAL NETWORKS 2.2 CATEGORY LEARNING 2.2.1 An Exemplar Theory: Context Theory 2.2.2 A Schema Theory: Adaptive Network Model 2.3 VALIDITY AND UTILIZATION 2.4 LEARNING EFFECTS OF CATEGORY LEARNING 2.5 EXPERIMENTS IN CATEGORY LEARNING 2.5.1 Experiment 1: Effects of Competing-Cue Validity 2.5.2 Experiment 2: Effects of Salience 2.5.3 Experiment 3: Interaction of Additional Irrelevant Dimensions and Salience CHAPTER 3 RESEARCH DESIGN 3.1 EXPERIMENT 1: EFFECTS OF COMPETING-CUE VALIDITY 3.2 EXPERIMENT 2: EFFECTS OF SALIENCE 3.3 EXPERIMENT 3: INTERACTION OF ADDITIONAL IRRELEVANT DIMENSIONS AND SALIENCE CHAPTER 4 EXPERIMENT RESULTS AND ANALYSIS 4.1 EXPERIMENT 1: EFFECTS OF COMPETING-CUE VALIDITY 4.2 EXPERIMENT 2: EFFECTS OF SALIENCE 4.3 EXPERIMENT 3: INTERACTION OF ADDITIONAL IRRELEVANT DIMENSIONS AND SALIENCE CHAPTER 5 SUMMARY AND FUTURE WORK 5.1 THE DISCUSSIONS FROM THE EXPERIMENTS 5.2 THE FUTURE WORK REFERENCES APPENDIX APPENDIX A APPENDIX B APPENDIX C zh_TW dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#A2002002097 en_US dc.subject (關鍵詞) 分類學習 zh_TW dc.subject (關鍵詞) 倒傳導神經網路 zh_TW dc.subject (關鍵詞) 敏感度分析 zh_TW dc.subject (關鍵詞) 競爭學習 zh_TW dc.subject (關鍵詞) 遮蔽效應 zh_TW dc.subject (關鍵詞) 不相關線索的影響 zh_TW dc.subject (關鍵詞) category learning en_US dc.subject (關鍵詞) back propagation neural networks en_US dc.subject (關鍵詞) sensitivity analysis en_US dc.subject (關鍵詞) competitive learning en_US dc.subject (關鍵詞) overshadowing en_US dc.subject (關鍵詞) the deleterious of an irrelevant cue en_US dc.title (題名) 倒傳導神經網路的有效性、使用性與顯著性之研究 zh_TW dc.title (題名) The Study of Validity, Utilization and Salience of the BP Networks en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 1. Anderson, J.R., Cognitive Psychology and Its Implications, W.H.Freeman, New York, 1990. 2. Anderson, J.R., Learning and Memory: An Integrated Approach, John Wiley and Sons, New York, 1995. 3. Boden, M.A., Artificial Intelligence in Psychology: Interdisciplinary Essays, The MIT Press, Cambridge, 1989. 4. Davey, G., Animal Learning and Conditioning, The Macmillan Press, London, 1981. 5. Edgell, S.E., ”Configural Information Processing in Two-Cue Probability Learning,” Organizational Behavior and Human Performance, Vol.22, 1978, pp.404-416. 6. Edgell, S.E. and Roe, R.M., “Dimensional Information Facilitates the Utilization of Configural Information: A Test of the Cestellan-Edgell and the Gluck-Bower Models,” Journal of Experimental Psychology: Learning, Memory, and Cognition, Vol.21, 1995, pp.1495-1508. 7. Gagne, R.M., “Memory Structures and Learning Outcomes,” Review of Educational Research, Vol.48, 1978, pp.178-222. 8. Gardner, H., The Mind’s New Science: A History of the Cognitive Revolution, Basic Books, New York, 1985. 9. Gluck, M.A. and Bower, G.H., “From Conditioning to Category Learning: An Adaptive Network Model,” Journal of Experimental Psychology: General, Vol.117, 1988, pp.227-247. 10. Grossberg, S., Neural Networks and Natural Intelligence, The MIT Press, Cambridge, 1988. 11. Kruschke J.K. and Johansen M.K., “A Model of Probabilistic Category Learning,” Journal of Experimental Psychology: Learning, Memory and Cognitive, Vol.25, 1999, pp.1083-1119. 12. Hertz, J., Krogh, A. and Palmer R.G., Introduction to the Theory of Neural Computation, Addison Wesley, New York, 1991. 13. Medin, D.L. and Edelson, S.M., “Problem Structure and the Use of Base-Rate Information from Experience,” Journal of Experimental Psychology: General, Vol.117, pp.68-85. 14. Medin, D.L. and Schaffer, M.M., “Context Theory of Classification Learning,” Psychological Review, Vol.85, 1978, pp.207-238. 15. Morris, R.G.M., Parallel Distributed Processing: Implications for Psychology and Neurobiology, Oxford, New York, 1989. 16. Nosofsky, R.M., “Similarity, Frequency, and Category Representations,”Journal of Experimental Psychology: Learning, Memory, and Cognition, Vol.14, 1988, pp.54-65. 17. Regehr, G. and Brooks, L., “Category Organization in Free Classification: The Organizing Effect of an Array of Stimuli,” Journal of Experimental Psychology: Learning, Memory, and Cognition, Vol.21, 1995, pp.347-363. 18. Rescorla, R.A. and Wagner, A.R., "A theory of Pavlovian Conditioning: Variations in the Effectiveness of Reinforcement and Non-reinforcement," In Black, A.H. and Prokasy, W.F. (Eds.), Classical Conditioning Ⅱ: Current Research and Theory, Appleton Century Crofts, New York, 1972. 19. Rumelhart, D.E., Hinton, G.E. and Williams, R.J., ”Learning Internal Representations by Error Propagation,” In Rumelhart, D.E. and McClelland, J. L. (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol.1, The MIT Press, Cambridge, 1986, pp.318-362. 20. Rumelhart, D.E. and McClelland, J.L. (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol.1, The MIT Press, Cambridge, 1986. 21. Schalkoff, R.J., Artificial Neural Networks, McGraw-Hill, New York, 1997. 22. Smith, J.D., Minda, J.P. and Murry, M.J., Jr., “Straight Talk about Linear Separability,” Journal of Experimental Psychology: Learning, Memory, and Cognition, Vol.23, 1997, pp.659-680. 23. Sutton, R.S. and Barto, A.G., “Toward a Modern Theory of Adaptive Networks: Expectation and Prediction,” Psychological Review, Vol.88, 1981, pp. 135-170. 24. Tsaih, R., “Sensitivity Analysis, Neural Networks, and the Finance,” International Joint Conference on Neural Networks, 1999. zh_TW
