Refer to the figure that illustrates the backpropagation multilayer network with layers. represents the number of neurons in th layer. Here, the network is presented the th pattern of training sample set with -dimensional input and -dimensional known output response . The actual response to the input pattern by the network is represented as . Let be the output from the th neuron in layer for th pattern; be the connection weight from th neuron in layer to th neuron in layer ; and be the error value associated with the th neuron in layer .
Again, the methodology of your work should be in strong accordance with the initial thesis and the main aim of your research. Visit the university library - the librarians might be eager to provide you with a good textbook as well as with a recommendation on how to start a cover letter . Thus, a lot of books can teach you research philosophy, so that you will be able to choose methods on your own. Moreover, it is convenient to look for someone else's thesis methodology example in the library. Remember, only deep theoretical knowledge can help you to reinforce your dissertation with firm methodological underpinnings.