Multiclass Pattern Recognition Extension for the New C-Mantec Constructive Neural Network Algorithm

Cognitive Computation

Volumn 2, Issue 4, 2010, Pages 285-290

  Subirats, José L ^a   Jerez, José M ^a   Gómez, Iván ^a   Franco, Leonardo ^a  

^a UNIVERSITY OF MÁLAGA   (Spain)

Author keywords

Multiclass pattern recognition; Neural networks; Supervised learning

Indexed keywords

BENCH-MARK PROBLEMS; CLASSIFICATION ALGORITHM; CONSTRUCTIVE NEURAL NETWORK ALGORITHM; DIFFERENT SIZES; MULTI-CLASS; MULTI-CLASS PROBLEMS; MULTICLASS PATTERN RECOGNITION; PATTERN CLASSIFICATION; PREDICTION ACCURACY;

ALGORITHMS; NETWORK ARCHITECTURE; PATTERN RECOGNITION; SUPERVISED LEARNING;

NEURAL NETWORKS;

EID: 78649936404     PISSN: 18669956     EISSN: 18669964     Source Type: Journal    
DOI: 10.1007/s12559-010-9051-6     Document Type: Article

References (14)

1. Haykin S. Neural networks: a comprehensive foundation. NY: Macmillan/IEEE Press; 1994.
2. Lawrence S, Giles CL, Tsoi AC. What size neural network gives optimal generalization ? Convergence properties of backpropagation. In: Technical report UMIACS-TR-96-22 and CS-TR-3617, Institute for Advanced Computer Studies, Univ. of Maryland. 1996.
3. Gómez I, Franco L, Jerez JM. Neural network architecture selection: Can function complexity help? Neural Process Lett. 2009; 30: 71-87.
4. Franco L, Elizondo D, Jerez JM, editors. Constructive neural networks. Berlin: Springer; 2010.
5. Smieja FJ. Neural network constructive algorithms: trading generalization for learning efficiency? Circuits Syst Signal Process. 1993; 12: 331-74.
6. do Carmo Nicoletti MC, Bertini JR. An empirical evaluation of constructive neural network algorithms in classification tasks. Int J Innov Comput Appl. 2007; 1: 2-13.
7. Mezard M, Nadal JP. Learning in feedforward layered networks: the tiling algorithm. J Phys A. 1989; 22: 2191-204.
8. Frean M. The upstart algorithm: a method for constructing and training feedforward neural networks. Neural Comput. 1990; 2: 198-209.
9. Parekh R, Yang J, Honavar V. Constructive neural-network learning algorithms for pattern classification. IEEE Trans Neural Netw. 2000; 11: 436-51.
10. Subirats JL, Jerez JM, Franco L. A new decomposition algorithm for threshold synthesis and generalization of Boolean functions. IEEE Trans Circuits Syst I. 2008; 55: 3188-96.
11. Ou G, Murphey YL. Multi-class pattern classification using neural networks. Pattern Recognit. 2007; 40: 418.
12. Subirats JL, Jerez JM, Franco L. A local stable learning rule and global competition for generating compact neural network architectures with good generalization abilities: the C-Mantec algorithm. Submitted. 2010.
13. Hawkins DM. The problem of overfitting. J Chem Info Comput Sci. 2004; 44: 1-12.
14. Prechelt L. Proben 1-A set of benchmarks and benchmarking rules for neural network training algorithms. Technical Report. 1994.