A Note on Sample Complexity of Learning Binary Output Neural Networks under Fixed Input Distributions
Year: 2010
Type: conference-paper
Abstract: We show that the learning sample complexity of a sigmoidal neural network constructed by Sontag (1992) required to achieve a given misclassification error under a fixed purely atomic distribution can grow arbitrarily fast: for any prescribed rate of growth there is an input distribution having this rate as the sample complexity, and the bound is asymptotically tight. The rate can be super exponential, a non-recursive function, etc. We further observe that Sontag's ANN is not Glivenko-Cantelli under any input distribution having a non-atomic part.
DOI: 10.1109/sbrn.2010.10
Author: V Pestov
Institution: University of Ottawa
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2148464719