Abstract: A method and system for accessing visually obscured data in a data processing system having a computer application displayed concurrently with a video image in a window which partially overlaps the computer application. The location of the video image within the window is maintained in relation to the visually obscured data within the computer application. The video image, which is comprised of a plurality of lines of video data, is then temporarily altered to a translucent state by omitting selected lines of video data. This renders the video image partially visible, allowing the visually obscured data within the computer application to be seen through the video image. The visually obscured data may now be visually accessed through the video image.

Abstract: A computer simulator is provided for displaying the state of an artificial neural network in a simplified yet meaningful manner on a computer display terminal. The user may enter commands to select one or more areas of interest within the neural network for further information regarding its state of learning and operation. One display mode illustrates the output activity of each neuron as representatively sized and shaded boxes within the border of the neuron, while another display mode shows the connectivity as weighted synapses between a user-selected neuron and the remaining neurons of the network in a similar manner. A third display mode provides a tuning curve wherein the synapses associated with each of the neurons are represented within the borders of the same. Both grid block and line graph type characterization are supported. The methodology allows large neural networks on the order of thousands of neurons to be displayed in a meaningful manner.