SAMPLE COMPLEXITY FOR FUNCTION LEARNING TASKS THROUGH LINEAR NEURAL NETWORKS
Arturo Hernández-Aguirre, Cris Koutsougeras, Bill P. Buckles · International Journal of Artificial Intelligence Tools · 2002
We find new sample complexity bounds for real function learning tasks in the uniform distribution by means of linear neural networks. These bounds, tighter than the distribution-free ones reported elsewhere in the literature, are applicable to simple functional link networks and radial basis neural networks.