Open Access. Powered by Scholars. Published by Universities.®
Digital Communications and Networking Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Digital Communications and Networking
Development Of Self-Adaptive Back Propagation And Derivative Free Training Algorithms In Artificial Neural Networks, Shamsuddin Ahmed
Development Of Self-Adaptive Back Propagation And Derivative Free Training Algorithms In Artificial Neural Networks, Shamsuddin Ahmed
Theses: Doctorates and Masters
Three new iterative, dynamically self-adaptive, derivative-free and training parameter free artificial neural network (ANN) training algorithms are developed. They are defined as self-adaptive back propagation, multi-directional and restart ANN training algorithms. The descent direction in self-adaptive back propagation training is determined implicitly by a central difference approximation scheme, which chooses its step size according to the convergence behavior of the error function. This approach trains an ANN when the gradient information of the corresponding error function is not readily available. The self- adaptive variable learning rates per epoch are determined dynamically using a constrained interpolation search. As a result, appropriate …
Bandwidth Management And Quality Of Service, Adalbert Engel
Bandwidth Management And Quality Of Service, Adalbert Engel
Theses: Doctorates and Masters
With the advent of bandwidth-hungry video and audio applications, demand for bandwidth is expected to exceed supply. Users will require more bandwidth and, as always, there are likely to be more users. As the Internet user base becomes more diverse, there is an increasing perception that Internet Service Providers (ISPs) should be able to differentiate between users, so that the specific needs of different types of users can be met. Differentiated services is seen as a possible solution to the bandwidth problem. Currently, however, the technology used on the Internet differentiates neither between users, nor between applications. The thesis focuses …