A learning method for vector field approximation by neural networks

Convolutional neural networks (CNNs) have been widely used in change detection of synthetic aperture radar (SAR) images and have been proven to have better precision than traditional methods. A two-stage patch-based deep learning method with a label updating strategy is proposed in this paper. The initial label and mask are generated at the pre-classification stage. Then a two-stage updating strategy is applied to gradually recover changed areas. At the first stage, diversity of training data is gradually restored. The output of the designed CNN network is further processed to generate a new label and a new mask for the following learning iteration. As the diversity of data is ensured after the first stage, pixels within uncertain areas can be easily classified at the second stage. Experiment results on several representative datasets show the effectiveness of our proposed method compared with several existing competitive methods.

Download Full-text

Vision-based Learning: A Novel Machine Learning Method based on Convolutional Neural Networks and Spiking Neural Networks

10.1109/icrom54204.2021.9663521 ◽

2021 ◽

Author(s):

Vahid Azimirad ◽

Saleh Valizadeh Sotubadi ◽

Ali Nasirlou

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Convolutional Neural Networks ◽

Spiking Neural Networks ◽

Machine Learning Method ◽

Learning Method

Download Full-text

Utilization of artificial neural networks and the TD-learning method for constructing intelligent decision support systems

European Journal of Operational Research ◽

10.1016/s0377-2217(99)00250-7 ◽

2000 ◽

Vol 122 (2) ◽

pp. 501-508 ◽

Cited By ~ 20

Author(s):

N. Baba ◽

H. Suto

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Decision Support ◽

Decision Support Systems ◽

Support Systems ◽

Learning Method ◽

Intelligent Decision ◽

Intelligent Decision Support Systems ◽

Artificial Neural ◽

Intelligent Decision Support

Download Full-text

Learning Method of Recurrent Spiking Neural Networks to Realize Various Firing Patterns using Particle Swarm Optimization

Proceedings of the 11th International Joint Conference on Computational Intelligence ◽

10.5220/0008164704790486 ◽

2019 ◽

Author(s):

Yasuaki Kuroe ◽

Hitoshi Iima ◽

Yutaka Maeda

Keyword(s):

Neural Networks ◽

Particle Swarm Optimization ◽

Particle Swarm ◽

Spiking Neural Networks ◽

Learning Method ◽

Swarm Optimization ◽

Firing Patterns

Download Full-text

QUANTUM FIELDS WITH MODIFIED DISPERSION RELATIONS IN CURVED SPACES

International Journal of Modern Physics D ◽

10.1142/s0218271811019086 ◽

2011 ◽

Vol 20 (05) ◽

pp. 745-756 ◽

Cited By ~ 2

Author(s):

FRANCISCO DIEGO MAZZITELLI

Keyword(s):

Vector Field ◽

General Structure ◽

Scalar Fields ◽

Field Approximation ◽

Weak Field ◽

Dispersion Relations ◽

Quantum Fields ◽

Renormalization Procedure ◽

Modified Dispersion Relations ◽

Weak Field Approximation

We discuss the renormalization procedure for quantum scalar fields with modified dispersion relations in curved spacetimes. We consider two different ways of introducing modified dispersion relations: through the interaction with a dynamical temporal vector field, as in the context of the Einstein–Aether theory, and breaking explicitly the covariance of the theory, as in Hǒrava–Lifshitz gravity. Working in the weak field approximation, we show that the general structure of the counterterms depends on the UV behavior of the dispersion relations and on the mechanism chosen to introduce them.

Download Full-text