Performance of generalized multilayered perceptons trained using the Levenberg-Marquardt method
Journal of Computing Sciences in Colleges
Neural network for graphs: a contextual constructive approach
IEEE Transactions on Neural Networks
Pose invariant face recognition using cellular simultaneous recurrent networks
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Putting more brain-like intelligence into the electric power grid: what we need and how to do it
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
R-POPTVR: a novel reinforcement-based POPTVR fuzzy neural network for pattern classification
IEEE Transactions on Neural Networks
Novel maximum-margin training algorithms for supervised neural networks
IEEE Transactions on Neural Networks
Local context discrimination in signature neural networks
IWINAC'11 Proceedings of the 4th international conference on Interplay between natural and artificial computation: new challenges on bioinspired applications - Volume Part II
Journal of Global Information Management
Hi-index | 0.00 |
Cellular simultaneous recurrent neural network (SRN) has been shown to be a function approximator more powerful than the multilayer perceptron (MLP). This means that the complexity of MLP would be prohibitively large for some problems while SRN could realize the desired mapping with acceptable computational constraints. The speed of training of complex recurrent networks is crucial to their successful application. This work improves the previous results by training the network with extended Kalman filter (EKF). We implemented a generic cellular SRN (CSRN) and applied it for solving two challenging problems: 2-D maze navigation and a subset of the connectedness problem. The speed of convergence has been improved by several orders of magnitude in comparison with the earlier results in the case of maze navigation, and superior generalization has been demonstrated in the case of connectedness. The implications of this improvements are discussed.