Litcius/Paper detail

Growing axons: greedy learning of neural networks with application to function approximation

Daria Fokina, Ivan Oseledets

2023Russian Journal of Numerical Analysis and Mathematical Modelling13 citationsDOI

Abstract

Abstract We propose a new method for learning deep neural network models, which is based on a greedy learning approach: we add one basis function at a time, and a new basis function is generated as a non-linear activation function applied to a linear combination of the previous basis functions. Such a method (growing deep neural network by one neuron at a time) allows us to compute much more accurate approximants for several model problems in function approximation.

Topics & Concepts

Basis (linear algebra)Artificial neural networkActivation functionBasis functionComputer scienceDeep learningGreedy algorithmFunction (biology)Artificial intelligenceFunction approximationMathematicsMathematical optimizationAlgorithmMathematical analysisGeometryEvolutionary biologyBiologyModel Reduction and Neural NetworksNeural Networks and ApplicationsNon-Destructive Testing Techniques
Growing axons: greedy learning of neural networks with application to function approximation | Litcius