Abstract
A high-order feedforward neural architecture, called pi t -sigma (? t ?) neural network, is proposed for lossy digital image compression and reconstruction problems. The ? t ? network architecture is composed of an input layer, a single hidden layer, and an output layer. The hidden layer is composed of classical additive neurons, whereas the output layer is composed of translated multiplicative neurons (? t -neurons). A two-stage learning algorithm is proposed to adjust the parameters of the ? t ? network: first, a genetic algorithm (GA) is used to avoid premature convergence to poor local minima; in the second stage, a conjugate gradient method is used to fine-tune the solution found by GA. Experiments using the Standard Image Database and infrared satellite images show that the proposed ? t ? network performs better than classical multilayer perceptron, improving the reconstruction precision (measured by the mean squared error) in about 56%, on average.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
