An Innovative Way to Measure the Quality of a Neural Network Without the Use of a Test Set

Journal of Advanced Computational Intelligence and Intelligent Informatics

Volumn 5, Issue 1, 2001, Pages 31-36

  Giovanni, Pilato ^b   Filippo, Sorbello ^a   Giorgio, Vassallo ^b  

^a UNIVERSITY OF PALERMO   (Italy)

^b Centro per la Ricerca Elettronica in Sicilia (CRES)   (Italy)

Author keywords

Generalization capability; Neural networks; Quality factors

Indexed keywords

COMPUTATIONAL COSTS; GENERALIZATION CAPABILITY; NEURAL UNITS; NEURAL-NETWORKS; OUTPUT FUNCTIONS; PRODUCTION PHASE; QUALITY FACTORS; TEST SETS; TRAINING PATTERNS; TRAINING SETS;

EID: 13844262008     PISSN: 13430130     EISSN: 18838014     Source Type: Journal    
DOI: 10.20965/jaciii.2001.p0031     Document Type: Article

References (16)

1. S. E. Fahlman and C. Lebiere. "The cascadccorrelalion learning architecture, advances in neural information processing systems." Advances in Neural Information Processing Systems. D.S.Touretzky ed., 2:524-532, 1990.
2. J. Friedman. "Multivariate adaptive regression splines." Technical Report, laboratory for Computational Statistics. Dept. of Statistics. Stanford University, (102). Nov 1988.
3. S. Gaglio. G. Pilato. F. Sorbcllo and G. Vassallo. "Usingthe Hermite Regression Formula to Design a Neural Architecture with Automatic Learning of the 'Hidden' Activation Functions". Lecture Notes in Artificial Intelligence - Selected Papers of the Sixth Congress of APIA. ATIA'99. Bologna (Italy), 226-237, Jan 2000 - Springer-Verlag.
4. G. A. M. Gioiello, A. Taranlino, F. Sorbello and G. Vassallo. " Simple techniques for an efficient recognition of handwritten characters using a mlp." The Journal of Intelligent Systems, 6(3/4):199-221, 1996.
5. Y. Hamamoto. S. Uchimura and S. Tomita. "On the behavior of artificial neural network classifiers in highdimensional spaces." IEEE Trans on PAMI. 18(5):571 -574. 19%.
6. http://www.cs.utoronto.ca/-delve.
7. J. N. Hwang. S. S. You. S. R. Lay and I. C. Jou. "What's wrong with a cascaded correlation learning network: a projection pursuit learning perspective." ftp://ftp.cis.ohiostate.edu/pub/neuroprosc
8. J. N. Hwang. S. R. Lay, M. Meachler. D. Martin and J. Shimcrt. " Regression modeling in backpropagation and in projection pursuit learning." IEEE Trans, on Neural Networks, 5(3):324—353. 1994.
9. S. N. J. Jack and J. Wang. "Weight smoothing to improve network generalization." IEEE Trans, on Neural Networks. 5(5):752-763, 1994.
10. W. H. Joerding and J. L. Meador. "Encoding a priori information in feedforward networks." Neural Networks. 4(6):847-856. 1991.
11. J. M. Minor. "Parity with two layered feedforward nets." Neural Networks, 6(5):705-707, 1993.
12. G. Pilato. F. Sorbello and G. Vassallo. "Using the hermite regression algorithm to improve the generalization capability of a neural network." XI Italian Workshop on Neural Nets WIRN'99 Vietri Sul Mare (SA) Italy, 2022 May 1999.
13. M. J. D. Powell. "Restart procedures for the conjugate gradient method." Mathematical Programming, 12:241-254. ll)77
14. R. Russell. J. Robert. I. Marks and O. Seho. "Similarities of error rcgularization. sigmoid gain scaling, target smoothing, and training with jitter." IEEE Trans, on Neural Networks. 6(3):529-538, 1995.
15. P. Simard, Y. Le Cun, J. Denker and B. Victorri. "An efficient algorithm for learning invarianccs in adaptive classifiers." Proc. of 11th I APR International Conference on Pattern Recognition, pages 651-655, 1994.
16. F. Sorbello, G. A. M. Gioiello and S. Vitabile. "Handwritten character recognition using a MLP" Chap. 5 of book: L. C. Jain. B. Lazzerini (eds) knowlcdgchased intelligent techniques in character recognition International series on computational intelligence. CRC Press, Erewhon, NC. 1999.