Rewriting Logic using Strategies for Neural Networks: an Implementation in Maude

In J. M. Corchado, S. Rodríguez, J. Llinas, and J. M. Molina, editors, International Symposium on Distributed Computing and Artificial Intelligence (DCAI 2008), volume 50 of Advances in Soft Computing, pages 424-433. Springer, 2008. © Springer-Verlag

Abstract: A general neural network model for rewriting logic is proposed. This model, in the form of a feedforward multilayer net, is represented in rewriting logic along the lines of several models of parallelism and concurrency that have already been mapped into it. By combining both a right choice for the representation operations and the availability of strategies to guide the application of our rules, a new approach for the classical backpropagation learning algorithm is obtained. An example, the diagnosis of glaucoma by using campimetric fields and nerve fibres of the retina, is presented to illustrate the performance and applicability of the proposed model.

[pdf]

@inproceedings{SantosPalominoVerdejo08,
    Author = {Gustavo Santos-Garc\'ia and Miguel Palomino and Alberto Verdejo},
    Booktitle = {International Symposium on Distributed Computing and Artificial Intelligence (DCAI 2008)},
    Editor = {Juan M. Corchado and Sara Rodr{\'\i}guez and James Llinas and  Jos\'e M. Molina},
    Pages = {424-433},
    Publisher = {Springer},
    Series = {Advances in Soft Computing},
    Title = {Rewriting Logic using Strategies for Neural Networks: an Implementation in {M}aude},
    Volume = 50,
    Year = 2008}