Self-organizing Neural System Research Articles

Modulation of the boundary between hierarchically differentiated domains in a self-organizing neural system

It is known that an abstract model with linear and distance-dependent interactions can develop a topographic connection structure in an input-output two-layer system. We expand the model by reflecting the effects of correlations between propagating neural firings and investigate the emergent properties in the resulting nonlinear model. It is found that the output layer can separate into several ones between which topographic connections develop. This result shows that hierarchically differentiated cortical sections, developing on a lattice structure, can regulate their boundary through Hebbian plasticity. We further argue that the phenomenon of cortical area differentiation can be described as a kind of phase transition.

A self-organizing neural system for learning to recognize textured scenes

A self-organizing ARTEX model is developed to categorize and classify textured image regions. ARTEX specializes the FACADE model of how the visual cortex sees, and the ART model of how temporal and prefrontal cortices interact with the hippocampal system to learn visual recognition categories and their names. FACADE processing generates a vector of boundary and surface properties, notably texture and brightness properties, by utilizing multi-scale filtering, competition, and diffusive filling-in. Its context-sensitive local measures of textured scenes can be used to recognize scenic properties that gradually change across space, as well as abrupt texture boundaries. ART incrementally learns recognition categories that classify FACADE output vectors, class names of these categories, and their probabilities. Top-down expectations within ART encode learned prototypes that pay attention to expected visual features. When novel visual information creates a poor match with the best existing category prototype, a memory search selects a new category with which classify the novel data. ARTEX is compared with psychophysical data, and is bench marked on classification of natural textures and synthetic aperture radar images. It outperforms state-of-the-art systems that use rule-based, backpropagation, and K-nearest neighbor classifiers.