A constructive algorithm to solve "Convex Recursive Deletion" (CoRD) classification problems via two-layer perceptron networks

IEEE Transactions on Neural Networks

Volumn 11, Issue 3, 2000, Pages 811-816

  Cabrelli, C ^a   Molter, U ^a   Shonkwiler, R ^b  

^a UNIVERSIDAD DE BUENOS AIRES   (Argentina)

^b GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Convex recursive deletion region; Neural network; Two layer perceptron

Indexed keywords

ALGORITHMS; BACKPROPAGATION; COMPUTATIONAL GEOMETRY; MATRIX ALGEBRA; MULTILAYER NEURAL NETWORKS; OPTIMIZATION; THEOREM PROVING; VECTORS;

CONVEX RECURSIVE DELETION REGION; TWO LAYER PERCEPTRON;

FEEDFORWARD NEURAL NETWORKS;

EID: 0034186968     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.846753     Document Type: Article

References (5)

1. J. Makhoul, A. El-Jaroudi, and R. Schwartz, "Formation of disconnected decision regions with a single hidden layer," in Proc. Int. Joint Conf. Neural Networks I. Washington, DC, 1989, pp. 455-460.
2. R. McCurley, K. Miller, and R. Shonkwiler, "Classification power of multiple-layer artificial neural networks," in SPIE 1990 Tech. Symp. Opt. Eng. Photon. Aerosp. Sensing; Program Opt./Neural Image Inform. Processing, vol. 1294, Orlando, FL, May 1990, pp. 577-587.
3. P. Rujan and M. Marchand, "A geometric approach to learning in neural networks," in Proc. Int. Joint Conf. Neural Networks II. Washington, DC, 1989, pp. 105-109.
4. R. Shonkwiler, "Separating the vertices of N-cubes by hyperplanes and its application to artificial neural networks," Trans. Neural Networks, vol. 4, pp. 343-347, Jan. 1993.
5. A. Wieland and R. Leighton, "Geometric analysis of neural network capabilities,"in Proc. 2nd IEEE Int. Conf. Neural Networks II. San Diego, CA, 1988, pp. 385-392.