A regularization term to avoid the saturation of the sigmoids in multilayer neural networks

DOI
10.1142/S0129065796000233
Serra-Ricart, M.; Gaitan, V.; Gomez, S.; Garrido, L.
Bibliographical reference

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, Volume 7, 257, pp. 6

Advertised on:
7
1996
Number of authors
4
IAC number of authors
1
Citations
0
Refereed citations
0
Description
In this paper we propose a new method to prevent the saturation of any set of hidden units of a multilayer neural network. This method is implemented by adding a regularization term to the standard quadratic error function, which is based on a repulsive action between pairs of patterns.
Type
Refereed

It may interest you

  • Refereed
    Copacabana: a probabilistic membership assignment method for galaxy clusters
    Cosmological analyses using galaxy clusters in optical/near-infrared photometric surveys require robust characterization of their galaxy content. Precisely determining which galaxies belong to a cluster is crucial. In this paper, we present the COlor Probabilistic Assignment of Clusters And BAyesiaNAnalysis (Copacabana) algorithm. Copacabana
    Esteves, J. H. et al.

    Advertised on:

    1
    2025
    Bibcode
    2025MNRAS.536..931E
    Citations
    1
  • Refereed
    Constraints on compact objects from the Dark Energy Survey 5-yr supernova sample
    Gravitational lensing magnification of Type Ia supernovae (SNe Ia) allows information to be obtained about the distribution of matter on small scales. In this paper, we derive limits on the fraction $\alpha$ of the total matter density in compact objects (which comprise stars, stellar remnants, small stellar groupings, and primordial black holes)
    Shah, P. et al.

    Advertised on:

    1
    2025
    Bibcode
    2025MNRAS.536..946S
    Citations
    0
  • Refereed
    Multiband Optical Variability of the Blazar 3C 454.3 on Diverse Timescales
    Due to its peculiar and highly variable nature, the blazar 3C 454.3 has been extensively monitored by the WEBT team. Here, we present for the first time these long-term optical flux and color variability results using data acquired in B, V, R, and I bands over a time span of about two decades. We include data from WEBT collaborators and public
    Dogra, Karan et al.

    Advertised on:

    1
    2025
    Bibcode
    2025ApJS..276....1D
    Citations
    0