A training-time analysis of robustness in feed-forward neural networks

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 4, Issue , 2004, Pages 2853-2858

  Alippi, Cesare ^a   Sana, Daniele ^b   Scotti, Fabio ^b  

^a POLITECNICO DI MILANO   (Italy)

^b UNIVERSITY OF MILAN   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

COMPLEX NEURAL NETWORKS; GAUSSIAN DISTRIBUTION; NETWORK ACCURACY; POLY-TIME COMPLEXITY;

ALGORITHMS; ERROR ANALYSIS; FINITE ELEMENT METHOD; PARAMETER ESTIMATION; PERSONNEL TRAINING; PERTURBATION TECHNIQUES; RESISTORS; ROBUSTNESS (CONTROL SYSTEMS);

NEURAL NETWORKS;

EID: 10944262663     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IJCNN.2004.1381110     Document Type: Conference Paper

References (12)

1. C. Alippi, "Application-Level Robustness and Redundancy in Linear Systems", IEEE Transactions on Circuits and Systems - 1:Fundamental Theory and Applications, Vol.49, No.7, 2002
2. C. Alippi, "Selecting Accurate, Robust and Minimal Feedforward Neural Networks", IEEE Transactions on Circuits and Systems - 1:Fundamental Theory and Applications, Vol.49, No.12, 2002.
3. C. Alippi, "Randomized Algorithms: A System-Level, Poly-Time analysis of robust computation", IEEE Transactions on Computers, Vol. 51, No. 7, 2002.
4. C. Alippi, V. Piuri, M. Sami, "Sensitivity in Errors in Artificial Neural Networks: A Behavioural Approach". IEEE Transactions on Circuits and Systems - 1:Fundamental Theory and Applications, Vol.42, No.6, 1995.
5. F.Blayo, Y. Cheneval, et.al."Enhanced Learning for Evolutive Neural Architecture", in Deliverable R3-B4-P TaskB4: Benchmarks, from Esprit Research Project Number 6891, 1995
6. H. Chernoff, "A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations", Ann. Math. Stat. 23, 1952.
7. C. Dundar, K. Rose, "The Effects of Quantization on Multilayer Neural Networks", IEEE Transactions on Neural Networks, Vol. 6, Pagg.1446-1451, 1995.
8. P.Koopman, Embedded systems Design Issues (the Rest of the Story), Proceedings of the IEEE-ICCD, 1996
9. J. Holt, J. Hwang, "Finite Precision Error Analysis of Neural Network Hardware Implementations", IEEE Transactions on Computers, Vol. 42, Pagg. 281-290, 1993.
10. K. Hornik, M. Stinchombe, and H. White, "Multilayer feedforward networks are universal approximators," in Neural Networks, vol. 2, 1989.
11. M. Stevenson, R. Winter, B. Widrow, "Sensitivity of Feedforward Neural Networks to Weigths Errors", IEEE Transaction on Neural Networks, Vol. 1, No. 1.
12. M. Vidyasagar, "An Overview of Computational Learning Theory and its Applications to Neural Network Training", Identification, Adaption, Learning, NATO ASI Series F, Vol. 153, Pagg. 400-422, 1996.