The design of the neural net based visual-robotic controller, controlling a tactile "itch-scratch" robotic sensory motor control system is presented. The "itch-scratch" robotic motor control system is described in referenced and linked publications. The design of the visual-robotic system is obtained by adding an obstacle avoiding visual system to the sensory motor control functions of the tactile "itch-scratch" robotic system. The visual-robotic controller is unique in that the coordinate frame in which the robot is operating, determined by the optical visual sensors, is reflected onto a neural network located within the robotic controller. The associated visual and tactile sensory motor control systems within the controller may lead to insight into the biological pathways in the brain for 3D-optical imaging and sensory motor control with feedback from the somatic body sensors.

The connectivity of a neural network model is designed to be similar to the biological connectivity of the somatic body sensors. The model consists of a mechanical robot controlled by a neural network based controller that adheres to three functional characteristics commonly associated with the subjective experience of sensory sensations (modalities of sensors): a) self knowledge, b) a "world space"-coordinate system in a controller, and c) access to information. The robotic controller, called a relational robotic controller (RRC)-circuit, controls the robotic body by reverse engineering the operation of the animal and human body and brain so that the functional operation adheres to those three functional characteristics. The RRC-circuit model may lead to a sensory-motor control system of the somatic motor system and insight into the biological pathways in the brain and the overall functional operation of the human body and brain.

Summary form only given. Survival prediction is important in cancer because it determines therapy, matches patients for clinical trials, and provides patient information. Is a backpropagation neural network more accurate at predicting survival, in breast cancer, than the current staging system? For over thirty years, cancer outcome prediction has been based on the pTNM staging system. There are two problems with this system: (1) it is not very accurate, and (2) its accuracy cannot be improved because predictive variables cannot be added to the model without increasing the model's complexity to the point where it is no longer useful to the clinician. The Surveillance, Epidemiology, and End Results data set, for the years 1977 - 1985, is used to compare the predictive accuracy of the current pTNM stage system to a backpropagation neural network, for five-year breast cancer survival. The c-index is the measure of accuracy. The pTNM stage system has a c-index of .69, while the backpropagation neural network, using the same three variables, has a c-index of .73 (SE for both models is less than .01). Using the same variables, the backpropagation neural network is significantly more accurate at predicting five year survival, in breast cancer, than the current pTNM stage system.>

A neural network architecture is introduced for incremental supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors, which may represent fuzzy or crisp sets of features. The architecture, called fuzzy ARTMAP, achieves a synthesis of fuzzy logic and adaptive resonance theory (ART) neural networks by exploiting a close formal similarity between the computations of fuzzy subsethood and ART category choice, resonance, and learning. Four classes of simulation illustrated fuzzy ARTMAP performance in relation to benchmark backpropagation and generic algorithm systems. These simulations include finding points inside versus outside a circle, learning to tell two spirals apart, incremental approximation of a piecewise-continuous function, and a letter recognition database. The fuzzy ARTMAP system is also compared with Salzberg's NGE systems and with Simpson's FMMC system.