Synaptic modulation based artificial neural networks
This work introduces complex processing neural network topologies, based on the concept of modulating neuron, which induce higher order terms by means of the modulation of the synaptic weights. These structures present the advantages of being very easy to train, adapting easily to changing contexts and offer very good generalization capabilities along all the dimensions of the problems they are trained to solve. Finally, the function each modulation level or each module performs is very clear, making it simple to extend the model to multilevel hierarchies.
Unable to display preview. Download preview PDF.
- Giles, C. L., and Maxwell, T., Learning, Invariance, and Generalization in High-Order Neural Networks, Applied Optics, Vol. 26, No. 23, December 1987.Google Scholar
- McCulloch, W. S., and Pitts, W., A Logical Calculus of the Ideas Immanent in Neural Activity, Bulletin of Mathematical Biophysics, Vol. 5, pp. 115–133, 1943.Google Scholar
- Dehaene, S., Changeux, J., and Nadal, J., Neural Networks that Learn Temporal Sequences by Selection, Procc. Natl. Acad. Sci. USA, Vol. 84, pp. 2727–2731, May 1987.Google Scholar
- Duro, R. J., Santos, J., and, Sarmiento, A., GENIAL, an Evolutionary Recurrent Neural Network Designer and Trainer. In Proceedings of CAST'94 (Fourth International Workshop on Computer Aided Systems Technology), Ottawa, Canada, May 1994.Google Scholar