Miguel Ángel Jaramillo Morán

A CNN Model for Grey Scale Image Processing

A modification of the CNN model is proposed in this work. An iterated-map is defined instead of the original differential equation while a sigmoid function is taken as the cell output. Modifications in the structure and values of the synaptic scheme allow the use of the model in different tasks. The networks behaviour is mainly determined by its feedforward term, while feedback simply adds optimization to the networks output The networks stability is discussed. Edge detection and contrast enhancement are performed, stressing the fact that they are only different aspects of the same network property: the enhancement of brightness gradients. Some examples are presented in which grey scale images are processed, revealing the capabilities of the model both in detecting edges and in enhancing contrasts.

A High Order Neural Model

The interaction between afferent nerves had always been regarded as a phenomenon which is produced outside the neuron. This work presents an extension of the classic concept of interaction between inputs, including the possibility of higher-order effects at the level of neuronal activity function. The mathematics is formulated with a view to its algorithmic simulation being implemented in a multiprocessor system by means of an adequate programming language running as a multi-elemental processor parallel computer. The system that is finally presented is a higher-ordered neural network with nonsupervised learning implemented in a multilayer structure.

ARQUITECTURA DE CONTROL ELECTRÓNICO EN CUADROS DE MANIOBRA DE MÁQUINAS DE CONTROL NUMÉRICO PARA CORTE POR PLASMA Y OXIGÁS

Nowadays cutting machines usually used in industry are controlled by a Computer Numeric Control (CNC) system working with a lot of signals which communicates with sensors and actuators in the machine through a control cabinet. In many cases this unit is designed by the cutting machine manufacturer (who is usually different from that of the CNC) and, as he is not a specialist in electronic design, the control cabinet is electrically implemented with the logic functions carried out in a discrete way by means of relays. This solution generates a hard wiring work when mounting onto the machine and makes it very difficult to repair when a failure is detected. This work presents a new electronic control system which replaces the old electrical one, with all its relays, usually used in this sort of machines. This new system has been tested in a plasma and oxifuel cutting machine. It has provided a noticeable reduction in the machine wiring and a simplification of the control cabinet design. These facts mean that the machine is now easier to assembly with an important reduction in purchasing and maintenance costs.

Image Quality Enhancement for Liquid Bridge Parameter Estimation with DTCNN

This work present the use of a neural structure to augment the quality of noisy images of liquid bridges to obtain a clear representation of its border in order to determine the acceleration that it is suffering. The used network is a three layers Discrete Time Cellular Neural Network in which the last one performs the contour highlighting through the adaptive definition of the gain and threshold of their output functions. Then an easy algorithm extracts a curve from the border.

Synthesis of Adaptive Memories with Neural Networks

The general formulation of bidirectional associative memories presents certain difficulties when the associations of pairs of patterns do not suppose a local energy minimun. To avoid these problems, the present paper describes an adaptive scheme which al lows the correlation matrix to be modified so as to reach the energy minimun while at the same time identifying the input patterns. The strategy described here allows the adaptation of the matrix to be performed for each external input, so that it can henceforth be described as a supervised type of training scheme. A consequence is its synthesis by means of neural networks with both the BAM and the adaptive mechanism itself integrated in distinct layers, allowing either of them to be changed without altering the other.

A Structured Development for the Implementation of a Multilayer Neural Network (Cram Project)

The main target of the CRAM (Computer Research on Associative Memory) Project is the practical implementation of a multilayer virtual Neural Network. The hardware used is a multiprocessor configuration IEEE 1014 Standard (VME Bus) with the 68020 CPU and the 68882 Floating Point Coprocessor running under the VersaDos Operating System, well suited for developing and debugging real-time programs.