Fernando Morgado Dias

Learn More
Artificial Neural Networks became a common solution for a wide variety of problems in many fields, such as control and pattern recognition to name but a few. Many solutions found in these and other Artificial Neural Network fields have reached a hardware implementation phase, either commercial or with prototypes. The most frequent solution for the(More)
This article describes the implementation in hardware of an Artificial Neural Network with an embedded Microprocessor in a FPGA. The implementation of a Neural Network in hardware can be desired to benefit from its distributed processing capacity or to avoid using a personal computer attached to each implementation. The relevance of implementing it in a(More)
Several implementations of Feedforward Neural Networks have been reported in scientific papers. These implementations do not allow the direct use of off-line trained networks. Usually the problem is the lower precision (compared to the software used for training) or modifications in the activation function. In the present work a hardware solution called(More)
It is commonly assumed that neural networks have a built in fault tolerance property mainly due to their parallel structures. The international community of Neural Networks discussed these properties only until 1994 and afterwards the subject has been mostly ignored. Recently the subject was again brought to discussion due to the possibility of using neural(More)
This paper presents a neural network implementation of the delay compensator to reduce the variable sampling to actuation delay effects in networked control systems. The compensator action is based on the knowledge of the sampling to actuation delay affecting the system and the control signal. It can be easily added to an existing control system that does(More)
In the literature the most common proposed solutions for training inverse neural models are the direct (or general) and specialized methods. The second one being considered as more reliable to produce correct inverse models has nevertheless some drawbacks in the implementation. The present paper introduces a hybrid solution that copes with the problems and(More)
The Levenberg-Marquardt algorithm is considered as the most effective one for training Artificial Neural Networks but its computational complexity and the difficulty to compute the trust region have made it very difficult to develop a true iterative version to use in on-line training. The algorithm is frequently used for off-line training in batch versions(More)
Artificial neural networks are a widespread tool with application in a variety of areas ranging from the social sciences to engineering. Many of these applications have reached a hardware implementation phase and have been documented in scientific papers. Unfortunately, most of the implementations have a simplified hyperbolic tangent replacement which has(More)