8 The training of some types of neural networks leads to separable non-linear least squares problems. These problems may be9 ill-conditioned and require special techniques. A robus...
Backpropagation of errors is not only hard to justify from biological perspective but also it fails to solve problems requiring complex logic. A simpler algorithm based on generati...
Abstract. By using differential neural networks, we present a novel robust adaptive controller for a class of unknown nonlinear systems. First, dead-zone and projection techniques...
The wide proliferation of wireless systems and the use of software radio technologies enables the employment of a heterogeneous network. In this concept services are delivered via...
Paul J. M. Havinga, Gerard J. M. Smit, Lars Kristi...
Linear projection equations arise in many optimization problems and have important applications in science and engineering. In this paper, we present a recurrent neural network fo...