A multi-layer network of sparse indicator neurons, trained by greedy boosting with random candidate search, is shown to be a universal approximator and to converge to a sample-optimal model eventually.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Constructive Universal Approximation and Sure Convergence for Multi-Layer Neural Networks
A multi-layer network of sparse indicator neurons, trained by greedy boosting with random candidate search, is shown to be a universal approximator and to converge to a sample-optimal model eventually.