Structural learning in artificial neural networks using sparse optimization

A1 Originalartikel i en vetenskaplig tidskrift (referentgranskad)


Interna författare/redaktörer


Publikationens författare: Mikael Manngård, Jan Kronqvist, Jari M. Böling
Publiceringsår: 2018
Tidskrift: Neurocomputing
Volym: 272
Artikelns första sida, sidnummer: 660
Artikelns sista sida, sidnummer: 667
eISSN: 1872-8286


Abstrakt

In this paper, the problem of simultaneously estimating the structure and parameters of artificial neural networks withmultiple hidden layers is considered. A method based on sparse optimization is proposed. The problem is formulated as an l0-norm minimization problem, so that redundant weights are eliminated from the neural network. Such problems are in general combinatorial, and are often considered intractable. Hence, an iterative reweighting heuristic for relaxing the l0-norm is presented. Experiments have been carried out on simple benchmark problems, both for classification and regression, and on a case study for estimation of waste heat recovery in ships. All experiments demonstrate the eectiveness of the algorithm.


Nyckelord

Artificial neural networks, Iterative Reweighting, Sparse optimization, Structural learning

Senast uppdaterad 2019-16-11 vid 03:15