|
| |
|
|
신경회로망을 이용한 기호적 지식의 개량
파일 
신경회로망을 이용한 기호적 지식의 개량.hwp
[Size :
320 Kbyte
]
신경회로망을 이용한 기호적 지식의 개량.hwp
[Size :
320 Kbyte
]
분량 17 Page
가격 2,000 원
×
링크주소가 복사 되었습니다.
원하는 곳에 붙혀넣기 하세요
원하는 곳에 붙혀넣기 하세요
카트
|
다운받기
|
 네이버 ID로 다운 받기  카카오 ID로 다운 받기  구글 ID로 다운 받기  페이스북 ID로 다운 받기 |
뒤로
|
자료설명
15.4.3 Splice-Junction 결정
두 번쩨 데이터집합은 splice-junction 결정인데, splice junction은 고등...
두 번쩨 데이터집합은 splice-junction 결정인데, splice junction은 고등...
본문/내용
15.4.3 Splice-Junction 결정
두 번쩨 데이터집합은 splice-junction 결정인데, splice junction은 고등동물에서 프로틴을 생성하는 과정에서 불필요한 DNA열이 제거되는데, 그 DNA열이 있는 위치이다. 데이터집합은 각각 60개의 뉴클레오티드들로 구성된 1,000개의 예제들이 있는데, 3가지 종류로 나뉘어 있다. 초기 규칙은 생물학 문헌에서 뽑은 21개의 규칙으로 하였고(여기에 보이지는 않았음), 이 규칙들은 대충 맞는 것이어서 예제들을 61%의 정확도로 분류해내었다.
15.5 규칙추출 실험
이 절에서는 앞에서 설명한 두 가지 규칙추출 방법의 장단점을 보이기 위한 실험의 결과를 제시한다. 평가 기준은 두 가지이다. 첫 번째는 질이다. 이것은 규칙의 정확도와 그 규칙이 추출된 네트웍을 규칙이 얼마나 충실히 표현하고 있는가 하는 것이다. 두 번째는 이해도이다. 이것은 추출된 개개의 규칙을 분석함으로써 알 수 있다.
15.5.1 테스트 방법
신경회로망을 학습시킬 때에 반복적 10겹 교차검증을 사용하였고, 학습 중 연결가중치를 감소시키는 방법을 사용하였으며, cross-entropy 오차 함수를 사용했다.
15.5.1.1 추출된 규칙의 정확도
추출된 규칙의 정확도를 보여주는 그림 15.10은 학습집합과 시험집합에 대한 오차 백분율을 10겹 교차검증을 10번 반복한 평균값으로 나타내며, 프로모터와 접합분할 문제에 대해서 그 결과를 보여주고 있다. 또, 비교를 위해 규칙추출 이전의 KBANN-net의 정확도를 Network이라는 꼬리표로 함께 그려놓았고, 프로모터 데이터집합에 대해서는 예제를 통해 직접 규칙을 고쳐나가는, 즉 “완전히 기호적인” EITHER 시스템의 정확도를 함께 그려놓았다.
그림 15.10: 추출된 규칙의 오인식률
Figure 15.10: The error rates of extracted rules
참고문헌
Blum, A., and Rivest, R.L., `Training a 3-node neural network is NP-complete,` Proceedings of the 1988 Workshop on Computational Learning Theory, pp. 9-18, Cambridge, MA, Morgan Kaufmann, San Mateo, CA, 1988.
Fisher, D.H., and McKusick, K.B., `An empirical comparison of ID3 and back-propagation,` Proceedings of the Eleventh International Joint Conference on Artifial Intelligence, pp. 788-793, Morgan Kaufmann, San Mateo, CA, 1989.
Fu, L.M., `Rule learning by searching on adapted nets,` Proceedings of the Ninth National Conference on Artificial Intelligence, pp. 590-595, AAAI Press, Menlo Park, CA, 1991.
Hartigan, J.A., Clustering Algorithms, Wiley, New York, 1975.
Hebb, D.O., The Organization of Behavior, Wiley, New York, 1949.
Hertz, J., Krogh, A., and Parlmer, R.G., Introduction to the Theory of Neural Computation, Addision Wesley, Reading, MA, 1991.
Hinton, G.E., `Connectionist learnig procedure,` Artificial Intelligence, Vol. 40, pp. 185-234, 1989.
IUB Nomenclature Committee, `Ambiguity codes,` European Journal of Biochemistry, Vol. 150, pp.1-5, 1985.
Jude, S., `On the complexity of loading shallow neural networks,` Journal of Complexity, Vol. 4, pp. 177-192, 1988.
Koudelka, G.B., Harrison, S.C., and Ptashne, M., `Effect of non-contacted bases on the affinity of 434 operator for 434 repressor and Cor.` Nature, Vol. 327, pp. 886-888, 1987.
Le Cun, Y., Denker, J.S., and Solla, S.A., `Optimal brain damage,` Advances in Neural Information Processing Systems, Vol. 2, pp. 598-605, Morgan Kaufmann, San Mateo, CA, 1989.
McCulloch, W.S., and Pitts, W.A., `A logical calculus of ideas immanent in nervous activity,` Bulletin of Mathematical Biophysics, Vol. 5, pp. 115-133, 1943.
McMillan, C., Mozer, M.C., and Smolensky, P., `The connectionist scientist game: Rule extraction and refinement in a neural network,` Proceedings of the Thirteenth Annual Conference of the Cognitive Science Society, pp. 424-430, Chicago, IL, Erlbaum, Hillsdale, NJ, 1991.
Mozer, M.C., and Smolensky, P., `Skeletonization: A technique for training the fat from a network via relevance assessment,` Advances in Neural Information Procesing Systems, Vol. 1, pp. 107-115, Morgan Kaufmann, San mateo, CA, 1988.
Murhy, P.M., and Pazzani, M.J., `ID2-of3: Constructive indection of N-of-M concepts for discriminatiors indecision tee,` Proceedings of the Eighth International Machine Lerning Workshop, pp. 183-187, Evanston, IL, Morgan Kaufmann, San Mateo, CA, 1991.
Noordewier, M.O., Towell, G.G., and Shavlik, J.W., `Training knowledge-based neural networks to recognize genes in DNA sequences,` Advances in Neural Information Processing Systems, Vol. 3, Morgan Kaufmann, San Mateo, CA, 1991.
NOwlan, S.J., and Hinton, G.E., `Simplifying neural networks by soft wseight-sharing,` Advances in Neural Information Processing Systems, Vol. 4, Morgan Kaufmann, San Mateo, CA, 1991.
Ourston, D., Using Explanation-based and Empirical Methods in Theory Revision, Ph.D. thesis, Department of Computer Sciences, University of Texas, Austin, TX, 1991.
Ourston, D., and Mooney, R.J., `Changing the rules: A comprehensive approach to theory refinement,` Proceedings of the Eighth National Conference on Artificial Intelligence, pp. 815-820, AAAI Press, Menlo Park, CA, 1990.
Pratt, L.Y., Mostow, J., and Kamm, C.A., `Direct transfer of learned information among neural networks,` Proceedings of the Ninth National Conference on Artificial Intelligence, pp. 815-820, AAAI Press, Menlo Park, CA, 1991.
Rosenblatt, F., Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms, Spartan, New York, 1962.
Rumelhart, D.E., Hinton, G.E., and Williams, R.J., `Learning internal representations by error propagation,` Parallel Distributed Processing: Explorations in the microstructure of cognition, Volume I: Foundations, Rumelhart, D.E., and McClelland, J.L., (eds.), pp. 318-363, MIT Press, Cambridge, MA, 1986.
Saito, K., and Nakano, R., `Medical diagnostic expert system based on PDP model,` Proceedings of IEEE International Conference on Neural Networks, Vol. 1, pp. 255-262, IEEE Computer Society, Washington, DC, 1988.
Sestito, S., and Dillon, T., `Using multi-layered neural networks for learning symbolic knowledge,` Proceedings of the 1990 Australian Artificial Intelligence Conference, Perth, Australia, 1990.
Shavlik, J.W., Mooney, R.J., and Towell, G.G., `Symbolic and neural net learning algorithms: An empirical comparison,` Machine Learning, Vol. 6, pp. 111-143, 1991.
Stormo, G.D., `Consensus patterns in DNA,` Methods in Enzymology, Vol. 183, pp. 211-221, Academic Press, San Diego, CA, 1990.
Thompson, K., Langley, P., and Iba, W., `Using background knowledge in concept formation,` Proceedings of the Eighth International Machine Learning Workshop, pp. 552-558, Evanston, IL, Morgan Kaufmann, San Mateo, CA, 1991.
Towell, G.G., Symbolic Knowledge and Neural Networks: Insertion, Refinement, and Extraction, Ph.D. thesis,Computer Sciences Department, University of Wisconsin, Madison, WI, 1991.
Towell, G.G., and Shavlik, J.W., `Interpretation of artificial neural networks: Mapping knowledge-based neural networks into rules,` Advances in Neural Informtion Processing Systems, Vol. 4, Morgan Kaufmann, San Mateo, CA, 1991.
Towell, G.G., Shavlik, J.W., and Craven, M.W., `Constuctive induciton in knowledge-based neural networks,` Proceedings of the Eighth International Machine Learning Workshop, pp. 213-217, Evanston, IL, Morgan Kaufmann, San Mateo, CA, 1991.
Towell, G.G., Shavlik, J.W., and Noordewier, M.O., `Refinement of approximately correct domain theories by knowledge-based neural networks,` Proceedings of the Eighth National Conference on Artificial Intelligence, pp. 861-866, AAAI Press, Menlo Park, CA, 1990.
Watson, J.D., Hopkins, H.H., Roberts, J.W., Steitz, J.A., and Weiner, A.M., The Molecular Biology of the Gene, Benjamin-Cummings, Menlo Park, CA, 1987.
Weigand, A.S., Rumelhart, D.E., and Huberman, B.A., `Generalization by weight-elimination with application to forecasting,` Advances in Neural Informtion Processing Systems, Vol. 3, pp. 875-882, Morgan Kaufmann, San Mateo, CA, 1990.
Weiss, S.M., and Kulikowski, C.A., Computer Systems That Learn, Morgan Kaufmann, San Mateo, CA, 1990.
Fisher, D.H., and McKusick, K.B., `An empirical comparison of ID3 and back-propagation,` Proceedings of the Eleventh International Joint Conference on Artifial Intelligence, pp. 788-793, Morgan Kaufmann, San Mateo, CA, 1989.
Fu, L.M., `Rule learning by searching on adapted nets,` Proceedings of the Ninth National Conference on Artificial Intelligence, pp. 590-595, AAAI Press, Menlo Park, CA, 1991.
Hartigan, J.A., Clustering Algorithms, Wiley, New York, 1975.
Hebb, D.O., The Organization of Behavior, Wiley, New York, 1949.
Hertz, J., Krogh, A., and Parlmer, R.G., Introduction to the Theory of Neural Computation, Addision Wesley, Reading, MA, 1991.
Hinton, G.E., `Connectionist learnig procedure,` Artificial Intelligence, Vol. 40, pp. 185-234, 1989.
IUB Nomenclature Committee, `Ambiguity codes,` European Journal of Biochemistry, Vol. 150, pp.1-5, 1985.
Jude, S., `On the complexity of loading shallow neural networks,` Journal of Complexity, Vol. 4, pp. 177-192, 1988.
Koudelka, G.B., Harrison, S.C., and Ptashne, M., `Effect of non-contacted bases on the affinity of 434 operator for 434 repressor and Cor.` Nature, Vol. 327, pp. 886-888, 1987.
Le Cun, Y., Denker, J.S., and Solla, S.A., `Optimal brain damage,` Advances in Neural Information Processing Systems, Vol. 2, pp. 598-605, Morgan Kaufmann, San Mateo, CA, 1989.
McCulloch, W.S., and Pitts, W.A., `A logical calculus of ideas immanent in nervous activity,` Bulletin of Mathematical Biophysics, Vol. 5, pp. 115-133, 1943.
McMillan, C., Mozer, M.C., and Smolensky, P., `The connectionist scientist game: Rule extraction and refinement in a neural network,` Proceedings of the Thirteenth Annual Conference of the Cognitive Science Society, pp. 424-430, Chicago, IL, Erlbaum, Hillsdale, NJ, 1991.
Mozer, M.C., and Smolensky, P., `Skeletonization: A technique for training the fat from a network via relevance assessment,` Advances in Neural Information Procesing Systems, Vol. 1, pp. 107-115, Morgan Kaufmann, San mateo, CA, 1988.
Murhy, P.M., and Pazzani, M.J., `ID2-of3: Constructive indection of N-of-M concepts for discriminatiors indecision tee,` Proceedings of the Eighth International Machine Lerning Workshop, pp. 183-187, Evanston, IL, Morgan Kaufmann, San Mateo, CA, 1991.
Noordewier, M.O., Towell, G.G., and Shavlik, J.W., `Training knowledge-based neural networks to recognize genes in DNA sequences,` Advances in Neural Information Processing Systems, Vol. 3, Morgan Kaufmann, San Mateo, CA, 1991.
NOwlan, S.J., and Hinton, G.E., `Simplifying neural networks by soft wseight-sharing,` Advances in Neural Information Processing Systems, Vol. 4, Morgan Kaufmann, San Mateo, CA, 1991.
Ourston, D., Using Explanation-based and Empirical Methods in Theory Revision, Ph.D. thesis, Department of Computer Sciences, University of Texas, Austin, TX, 1991.
Ourston, D., and Mooney, R.J., `Changing the rules: A comprehensive approach to theory refinement,` Proceedings of the Eighth National Conference on Artificial Intelligence, pp. 815-820, AAAI Press, Menlo Park, CA, 1990.
Pratt, L.Y., Mostow, J., and Kamm, C.A., `Direct transfer of learned information among neural networks,` Proceedings of the Ninth National Conference on Artificial Intelligence, pp. 815-820, AAAI Press, Menlo Park, CA, 1991.
Rosenblatt, F., Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms, Spartan, New York, 1962.
Rumelhart, D.E., Hinton, G.E., and Williams, R.J., `Learning internal representations by error propagation,` Parallel Distributed Processing: Explorations in the microstructure of cognition, Volume I: Foundations, Rumelhart, D.E., and McClelland, J.L., (eds.), pp. 318-363, MIT Press, Cambridge, MA, 1986.
Saito, K., and Nakano, R., `Medical diagnostic expert system based on PDP model,` Proceedings of IEEE International Conference on Neural Networks, Vol. 1, pp. 255-262, IEEE Computer Society, Washington, DC, 1988.
Sestito, S., and Dillon, T., `Using multi-layered neural networks for learning symbolic knowledge,` Proceedings of the 1990 Australian Artificial Intelligence Conference, Perth, Australia, 1990.
Shavlik, J.W., Mooney, R.J., and Towell, G.G., `Symbolic and neural net learning algorithms: An empirical comparison,` Machine Learning, Vol. 6, pp. 111-143, 1991.
Stormo, G.D., `Consensus patterns in DNA,` Methods in Enzymology, Vol. 183, pp. 211-221, Academic Press, San Diego, CA, 1990.
Thompson, K., Langley, P., and Iba, W., `Using background knowledge in concept formation,` Proceedings of the Eighth International Machine Learning Workshop, pp. 552-558, Evanston, IL, Morgan Kaufmann, San Mateo, CA, 1991.
Towell, G.G., Symbolic Knowledge and Neural Networks: Insertion, Refinement, and Extraction, Ph.D. thesis,Computer Sciences Department, University of Wisconsin, Madison, WI, 1991.
Towell, G.G., and Shavlik, J.W., `Interpretation of artificial neural networks: Mapping knowledge-based neural networks into rules,` Advances in Neural Informtion Processing Systems, Vol. 4, Morgan Kaufmann, San Mateo, CA, 1991.
Towell, G.G., Shavlik, J.W., and Craven, M.W., `Constuctive induciton in knowledge-based neural networks,` Proceedings of the Eighth International Machine Learning Workshop, pp. 213-217, Evanston, IL, Morgan Kaufmann, San Mateo, CA, 1991.
Towell, G.G., Shavlik, J.W., and Noordewier, M.O., `Refinement of approximately correct domain theories by knowledge-based neural networks,` Proceedings of the Eighth National Conference on Artificial Intelligence, pp. 861-866, AAAI Press, Menlo Park, CA, 1990.
Watson, J.D., Hopkins, H.H., Roberts, J.W., Steitz, J.A., and Weiner, A.M., The Molecular Biology of the Gene, Benjamin-Cummings, Menlo Park, CA, 1987.
Weigand, A.S., Rumelhart, D.E., and Huberman, B.A., `Generalization by weight-elimination with application to forecasting,` Advances in Neural Informtion Processing Systems, Vol. 3, pp. 875-882, Morgan Kaufmann, San Mateo, CA, 1990.
Weiss, S.M., and Kulikowski, C.A., Computer Systems That Learn, Morgan Kaufmann, San Mateo, CA, 1990.
| 📝 Regist Info |
|
I D : anaw***** Date : 2012-08-20 FileNo : 16059162 |
Cart  | |
| |