Title :
Bounds on the number of samples needed for neural learning
Author :
Mehrotra, Kishan G. ; Mohan, Chilukuri K. ; Ranka, Sanjay
Author_Institution :
Sch. of Comput. & Inf. Sci., Syracuse Univ., NY, USA
fDate :
11/1/1991 12:00:00 AM
Abstract :
The relationship between the number of hidden nodes in a neural network, the complexity of a multiclass discrimination problem, and the number of samples needed for effect learning are discussed. Bounds for the number of samples needed for effect learning are given. It is shown that Ω(min (d,n) M) boundary samples are required for successful classification of M clusters of samples using a two-hidden-layer neural network with d-dimensional inputs and n nodes in the first hidden layer
Keywords :
computational complexity; learning systems; neural nets; pattern recognition; boundary samples; classification; complexity; hidden nodes; multiclass discrimination; neural learning; pattern recognition; two-hidden-layer neural network; Information science; Multi-layer neural network; Neural networks; Performance evaluation; System testing;
Journal_Title :
Neural Networks, IEEE Transactions on
