loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Diego Santiago de Meneses Carvalho 1 and Areolino de Almeida Neto 2

Affiliations: 1 Department of Computing, IFMA, Sao Luis and Brazil ; 2 Department of Informatics, UFMA, Sao Luis and Brazil

Keyword(s): Artificial Neural Networks, Momentum Term, Correlation Coefficient, BP with Selective Momentum.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Biomedical Engineering ; Biomedical Signal Processing ; Computational Intelligence ; Health Engineering and Technology Applications ; Human-Computer Interaction ; Methodologies and Methods ; Neural Networks ; Neurocomputing ; Neurotechnology, Electronics and Informatics ; Pattern Recognition ; Physiological Computing Systems ; Sensor Networks ; Signal Processing ; Soft Computing ; Theory and Methods

Abstract: In many cases it is very hard to get an Artificial Neural Network (ANN) suitable for learning the solution, i.e., it cannot acquire the desired knowledge or needs an enormous number of training iterations. In order to improve the learning of ANN type Multi-Layer Perceptron (MLP), this work describes a new methodology for selecting weights, which will have the momentum term added to variation calculus of their values during each training iteration via Backpropagation (BP) algorithm. For that, the Pearson or Spearman correlation coefficients are used. Even very popular, the usage of BP algorithm has some drawbacks, among them the high convergence time is highlighted. A well-known technique used to reduce this disadvantage is the momentum term, which tries to accelerate the ANN learning keeping its stability, but when it is applied in all weights, as commonly used, with inadequate parameters, the result can be easily a failure in the training or at least an insignificant reduction of th e ANN training time. The use of the Selective Momentum Term (SMT) can reduce the training time and, therefore, be also used for improving the training of deep neural networks. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.163.200.109

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Carvalho, D. and Neto, A. (2019). Acceleration of Backpropagation Training with Selective Momentum Term. In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-350-6; ISSN 2184-433X, SciTePress, pages 443-450. DOI: 10.5220/0007272004430450

@conference{icaart19,
author={Diego Santiago de Meneses Carvalho. and Areolino de Almeida Neto.},
title={Acceleration of Backpropagation Training with Selective Momentum Term},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2019},
pages={443-450},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007272004430450},
isbn={978-989-758-350-6},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Acceleration of Backpropagation Training with Selective Momentum Term
SN - 978-989-758-350-6
IS - 2184-433X
AU - Carvalho, D.
AU - Neto, A.
PY - 2019
SP - 443
EP - 450
DO - 10.5220/0007272004430450
PB - SciTePress