Abstract
Method for visualization of learning processes for back propagation neural network is proposed. The proposed method allows monitor spatial correlations among the nodes as an image and also check a convergence status. The proposed method is attempted to monitor the correlation and check the status for spatially correlated satellite imagery data of AVHRR derived sea surface temperature data. It is found that the proposed method is useful to check the convergence status and also effective to monitor the spatial correlations among the nodes in hidden layer.
Highlights
Back Propagation Neural Network: BPNN is widely used method for machine learning and optimization method
The neural network which will be call All Nodes Linked Neural Network: ANLNN hereafter, does not have the same structure like a typical one, each node on a layer will only link to a specify node or specify nodes on connected layer
The ANLNN and typical structure neural network will be tried to apply in recognizing integer numbers
Summary
Back Propagation Neural Network: BPNN is widely used method for machine learning and optimization method. One of the problems of BPNN is that it cannot ensure to find global optimum solution and can find one of local minima. It is difficult to check convergence status; residual error can be monitored though. Method for visualization of convergence processes and spatial correlation of nodes in hidden layer of BPNN is proposed
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: International Journal of Advanced Computer Science and Applications
Disclaimer: 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.