Abstract: A method for hierarchical visualization of multi-dimensional data is provided. A first dimension-reduction process is applied to a multi-dimensional data set to obtain a first visualization. A subset of the multi-dimensional data set associated with a selected region of the dimension-reduced first visualization is selected. A second dimension-reduction process is applied to the selected subset of the multi-dimensional data set to obtain at least one additional visualization.

Abstract: Method of incrementally forming and adaptively updating a neural net model are provided. A function approximation node is incrementally added to the neural net model. Function parameters for the function approximation node are determined and function parameters of other nodes in the neural network model are updated, by using the function parameters of the other nodes prior to addition of the function approximation node to the neural network model.

Abstract: A model maintenance method is provided. If accuracy of prediction by a current model through consultation with new data is determined to be below a predetermined threshold, a compound model is formed by supplementing the current model with a local net trained with the new data.

Abstract: The subject system provides reduced-dimension mapping of pattern data. Mapping is applied through conventional single-hidden-layer feed-forward neural network with non-linear neurons. According to one aspect of the present invention, the system functions to equalize and orthogonalize lower dimensional output signals by reducing the covariance matrix of the output signals to the form of a diagonal matrix or constant times the identity matrix. The present invention allows for visualization of large bodies of complex multidimensional data in a relatively “topologically correct” low-dimension approximation, to reduce randomness associated with other methods of similar purposes, and to keep the mapping computationally efficient at the same time.

Abstract: The subject system provides reduced-dimension mapping of pattern data. Mapping is applied through conventional single-hidden-layer feed-forward neural network with non-linear neurons. According to one aspect of the present invention, the system functions to equalize and orthogonalize lower dimensional output signals by reducing the covariance matrix of the output signals to the form of a diagonal matrix or constant times the identity matrix. The present invention allows for visualization of large bodies of complex multidimensional data in a relatively “topologically correct” low-dimension approximation, to reduce randomness associated with other methods of similar purposes, and to keep the mapping computationally efficient at the same time.

Abstract: The subject system provides reduced-dimension mapping of pattern data. Mapping is applied through conventional single-hidden-layer feed-forward neural network with non-linear neurons. According to one aspect of the present invention, the system functions to equalize and orthogonalize lower dimensional output signals by reducing the covariance matrix of the output signals to the form of a diagonal matrix or constant times the identity matrix. The present invention allows for visualization of large bodies of complex multidimensional data in a relatively "topologically correct" low-dimension approximation, to reduce randomness associated with other methods of similar purposes, and to keep the mapping computationally efficient at the same time.

Abstract: A parallel, distributed processing system is provided for solving NP-hard problems, and the like, efficiently, quickly and accurately. The system employs parallel processors which are iteratively and intelligently allocated for a series of generations of child solutions from selected, previous generation or parent solutions. The system employs multiple levels of competition for generating a next level of possible solutions and for reallocating processor resources to the most promising regions for finding a best solution to the task. This includes both inter-family competition, as well as intra-family competition. System temperature data are set and gradually decreased with each succeeding generation. A degree of randomness is entered into the solution generation. The hierarchical and iterative process, incorporating randomness and a decreasing temperature provides for the guided evolutionary simulated annealing solution generation.

Abstract: The subject system provides a self-organized reduced-dimension remapping of pattern data. The system functions to a mapping from an original pattern space to a reduced-dimension space in an unsupervised nonlinear manner, but with a constraint that the overall variance in a representation of the data be conserved. This approach relates to but is different from both the Karhuren-Loeve (K-L) transform and auto-associative approaches which emphasize feature extraction, and also from the Advanced Reasoning Tool (ART) and feature mapping approaches which emphasize category formation based on similarity in the original representation. The subject system is highly efficient computationally. The reduced-dimension representation is suitably further simplified with ART or feature mapping techniques, as appropriate and as desired.

Abstract: In the design of the process to machine discrete mechanical parts, the sequence of removing material is arrived at to ensure that the resulting part is of the correct geometry and finish, and the process is safe, feasible and accomplished in minimum time. For complex parts, an experienced machinist makes use of inductive methods to relate similar part material, geometries together with interdependencies and their associated machining sequences which have produced quality parts in the past with minimum time expended, or deductive methods to generate a sequence by relating feature attributes (relative size and position) and relations (intersections and common tooling). Of interest is the interaction between the two methods because their coupling enables a self-improving design system to be realized. A feature-based solid modelling software environment provides the elements of a symbolic language for describing a discrete mechanical part in terms of its product and process design.

Abstract: A neural network system includes means for accomplishing artificial intelligence functions in three formerly divergent implementations. These functions include: supervised learning, unsupervised learning, and associative memory storage and retrieval. The subject neural network is created by addition of a non-linear layer to a more standard neural network architecture. The non-linear layer functions to expand a functional input space to a signal set including orthonormal elements, when the input signal is visualized as a vector representation. An input signal is selectively passed to a non-linear transform circuit, which outputs a transform signal therefrom. Both the input signal and the transform signal are placed in communication with a first layer of a plurality of processing nodes. An improved hardware implementation of the subject system includes a highly parallel, hybrid analog/digital circuitry.

Abstract: A method for producing a pattern for making a cast part is described which comprises the steps of defining the structure of the part in terms of computer aided design system data, selecting a parting surface for the part to be cast; defining core requirements for the part by sweeping each positive feature of the part to the parting surface, subtracting the part from the projection, adding any remaining volume to the core, sweeping negative features away from the parting surface to the top or bottom of the mold and subtracting the negative features from the projection and intersecting the remainder of the part and adding any remaining volume to the core; repetitively generating alternative parting surfaces for the part and defining the corresponding core requirements whereby an optimum parting surface is defined for which the quantity and complexity of the corresponding core requirements are minimized, constructing core prints for each core requirement; constructing a pattern by adding the core prints to the p