Abstract
A new and fast technique to determine the convergence of iterated neural networks is presented. Test vectors are derived to determine the convergence of the output function in the presence of stuck-at faults.<>
The Twenty-Third Southeastern Symposium on System Theory
Like what you’re reading?
Already a member?
Related Articles
- Conditional Event Algebra Techniques for Iterated Image Estimation
Proceedings of International Conference on Image Processing - Iterated Runge-Kutta methods on distributed memory multiprocessors
3rd Euromicro Workshop on Parallel and Distributed Processing - A Neural Network Blind Multi-user Detection Algorithm
2009 International Conference on Measuring Technology and Mechatronics Automation - Extrapolation of Discrete Multi-projection Methods for Fredholm Integral Equations of the Second Kind
2017 13th International Conference on Computational Intelligence and Security (CIS) - The converging unlearning algorithm for the Hopfield neural network: optimal strategy
Proceedings of 12th International Conference on Pattern Recognition - Parallel Asynchronous Modified Newton Methods for Network Flows
2015 IEEE International Parallel and Distributed Processing Symposium Workshop (IPDPSW) - An Improved Iterative Algorithm of Neural Network for Nonlinear Equation Groups
2012 Second International Conference on Business Computing and Global Informatization - A Fast Iterated Orthogonal Projection Framework for Smoke Simulation
IEEE Transactions on Visualization & Computer Graphics - Visual Explanations via Iterated Integrated Attributions
2023 IEEE/CVF International Conference on Computer Vision (ICCV) - A Cross Iterative Algorithm for Mining Communities in Bipartite Network
2021 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE)