Titlebook: Neural Computers; Rolf Eckmiller,Christoph Malsburg Conference proceedings 1989 Springer-Verlag Berlin Heidelberg 1989 artificial intellig

Heretical

Image Segmentation with Neurocomputershen the objects portrayed in that image are recognized. or at least characterized. An object is characterized in terms of the segments of the image that it subtends. An image segment. is a collection of pixels that satisfies certain conditions of adjacency and similarity.

DIS

A Hierarchical Neural Network Model for Selective Attentiontches its attention to recognize another pattern. The model also has the ability to restore an imperfect pattern, and can recall the complete pattern in which the defects have been corrected and the noise eliminated. These functions are performed successfully even if the input patterns are deformed in shape or shifted in position.

開(kāi)頭

glisten

A Cortical Network Model for Early Vision Processingry feature extractor by responding preferentially to striped, checked or other high-symmetry patterns. We find that the model can act in something like this way in a particular region of its parameter space, but that such behaviour is incompatible with the reconstruction of local detail.

解決

哀悼

Parallelism and Redundancy in Neural Networksancy, and a balanced distribution of processing tasks between all subsystems. As a result, reliability and accuracy of computation become exchangable. We present examples for these principles of biological information processing and discuss how parallelism is used for their implementation.