Abstract: A computer object processing system for, during selected iterations, generating an object, such as an expression defining an image. During an initial iteration, a predetermined number of seed objects are generated, each seed object defining an object for the initial iteration. During each successive iteration, a predetermined number of mutated objects are generated (i) in response to an operator selected one of the seed objects during the initial iteration and (ii) in response to a an operator selected object during each iteration after the initial iteration. During each iteration one of the seed objects or one of the mutated objects is selected for use in generating a mutated object during a subsequent iteration.

Abstract: A framework for use with object-oriented programming systems provides a case-based reasoning (CBR) system shell that permits a framework user to develop a case base having case histories and generates a case-based reasoning system that receives user requests for query solutions and produces a query solution that can be incorporated into the case base. The framework includes a Session component that controls processing of the CBR system, a Control Flow component that manages the extension of the categories and classes of the OO framework, a Data Store component that stores persistent case structure definitions, case instances, and a change log, a Presentation component that manages the user interface to the CBR system user, and a Query Engine that evaluates a received query against the case base. The case definitions and case base descriptions comprise a set of object oriented classes that are organized into an inheritance hierarchy.

Abstract: The intelligent motion surface disclosed herein includes multiple cells, each cell having independently controllable force producing devices for moving the object in multiple directions parallel to the intelligent motion surface. The intelligent motion surface has within each cell a set of driving devices engaging with the force producing devices for independent operation. Each driving device propels the motion surface in a separate direction. A motion controller independently operates each of the force producing devices to move the object. The motion controller delineates at least one force area on the intelligent motion surface based on object shape, object size, and desired position of the object on the intelligent motion surface, and provides translation of the desired force areas to produce a desired force vector on the intelligent motion surface.

Abstract: An object-oriented programming system which performs equivalent conversion on a class network structure.Program data including class data and relation data in entered from the class data input section (4) and the relation data input section (5). Program data is stored in the class data file (6) and relation data file (7). The range of equivalent conversion is entered from the conversion range input section (8), and an equivalent conversion mode is entered from the conversion mode input section (9). The equivalent conversion section (10) converts the program data based on the range and the mode. The output range of program data is entered from the display range input section (12), and the output format of program data is entered from the display format input section (13). The generation section (11) generates the display data of the program data in the diagram format. The display unit (2) displays the diagram of the display data.

Abstract: A method to operate a computerized adaptive knowledge base. The contents and organization of the adaptive knowledge base evolve based on the contributions and evaluations of a user community. Whether a particular set of contents or an alternative organization is preserved for future iterations is a function of user evaluations, taking into account the amounts of information and the relative importance of content vis-a-vis organization. Items of the adaptive knowledge base which are as yet unevaluated by a particular user are ranked by estimating that user's evaluations, based on other items for which evaluations are available to compare with other users. For example, evaluations are estimated from regressions with other users, weighted by functions of the correlation coefficients, the number of observations in common, and the significance of those observations for the particular user in the sense that their evaluation differs from the mean evaluation.

Abstract: This invention provides learning methods in binary systems by modifying the connected states of the circuit among each basic binary gate in binary combined logical and sequential circuits composed with basic binary gates such as AND, OR, NOT, NAND, NOR and EXOR gates. As the pseudo-neuron theory and the pseudo-potential energy theory are skillfully introduced, it is possible to attain specified learning effects during a very short learning period. Further, as implementation of the learning methods into the conventional computer and other digital equipment is simple, it is expected to be used widely in wide application, for example, such as in image processing, voice processing or natural word processing.

Abstract: The method of the invention analyzes program components from a program to determine a set of subroutines whose execution time, for increasing input data set sizes, is predicted to increase at a rate that is more rapid than the rate exhibited by other subroutines in the program. The method of the invention includes the steps of: applying a plurality of different size data sets to the program; executing the program with each different size data set; determining execution times for each program component in the program for execution runs of the program; analyzing the execution times for each program component to determine a set of finite differences between execution times, during succeeding runs; and determining from sets of finite differences, which program components exhibit a largest growth in execution time, for increasing sizes of input data set size.

Abstract: A microprocessor operates in response to microinstructions stored in a read only memory. A patch table stores a indication of patch microinstructions stored in cache memory. This cache memory caches data and/or macroinstructions for the microprocessor. Each new microaddress is compared with the patch table entries. If there in no match, then a multiplexer selects the microinstruction recalled from that microinstruction address within the microinstruction read only memory. If there is a match, then a corresponding patch microinstruction is recalled from the cache memory. The multiplexer selects this patch microinstruction. The microprocessor operates under the control of the selected microinstruction. This technique enables a fix of faulty microinstructions in the field, by supplying the computer user with the patch microinstructions. Using a portion of the cache memory to store the patch microinstructions eliminates any problem with specifying too large or too small a memory for patch microinstructions.

Abstract: A utility with which a programmer can generate or alter computer code for a calendaring function, and test the code prior to compilation. Entering the program in edit mode, the programmer locates a portion of the program where code for a calendaring function is to be generated or altered, and invokes the date logic generator. The date logic generator provides an initial window with a choice of calendaring functions, and upon selecting a calendaring function, a parameters window displaying a number of first-level parameters for that function is provided. Depending on the specification of the values of the first-level parameters, sub-windows with second-level parameters may be provided. And, in general, depending on the specification of the values of the n-level parameters, (n+1)-level parameters may be provided in sub-windows. The parameters provided at any instant are only those which have already been specified or those that require specification.

Abstract: A knowledge base search and retrieval system, which includes factual knowledge base queries and concept knowledge base queries, is disclosed. A knowledge base stores associations among terminology/categories that have a lexical, semantical or usage association. Document theme vectors identify the content of documents through themes as well as through classification of the documents in categories that reflects what the documents are primarily about. The factual knowledge base queries identify, in response to an input query, documents relevant to the input query through expansion of the query terms as well as through expansion of themes. The concept knowledge base query does not identify specific documents in response to a query, but specifies terminology that identifies the potential existence of documents in a particular area.

Abstract: A system is disclosed that provides a goal based learning system utilizing a rule based expert training system to provide a cognitive educational experience. The system provides the user with a simulated environment that presents a business opportunity to understand and solve optimally. Mistakes are noted and remedial educational material presented dynamically to build the necessary skills that a user requires for success in the business endeavor. The system utilizes an artificial intelligence engine driving individualized and dynamic feedback with synchronized video and graphics used to simulate real-world environment and interactions. Multiple "correct" answers are integrated into the learning system to allow individualized learning experiences in which navigation through the system is at a pace controlled by the learner.

Abstract: A sequence of measured quantities is determined for a chemical reactor and a data generator generates a curve in normal coordinates from a respective predetermined normal form that describes a type of critical state. Each normal form is imaged onto the sequence of measured quantities by neural networks whereby a respective neural network is allocated to a data generator. The imaging is optimized by applying parameter optimization methods. The neural network that converges best through use of parameter optimization method describes the critical state that lies closest to the actual state of the chemical reactor.

Abstract: A learning system is used in a data processing apparatus for learning an input pattern by obtaining an internal-state value necessary for realizing a desired data conversion by performing a pattern conversion defined by the internal-state value and calculating an output pattern corresponding to the input pattern.

Abstract: A signal processing apparatus and concomitant method for learning and integrating features from multiple resolutions for detecting and/or classifying objects are presented. Neural networks in a pattern tree structure with tree-structured descriptions of objects in terms of simple sub-patterns, are grown and trained to detect and integrate the sub-patterns. A plurality of objective functions and their approximations are presented to train the neural networks to detect sub-patterns of features of some class of objects. Objective functions for training neural networks to detect objects whose positions in the training data are uncertain and for addressing supervised learning where there are potential errors in the training data are also presented.

Abstract: A device for generating useful information employing a first neural network trained to produce input-output maps within a predetermined initial knowledge domain, an apparatus for subjecting the neural network to perturbations which may produce changes in the predetermined knowledge domain, the neural network having an optional output for feeding the outputs of the first neural network to a second neural network that evaluates the outputs based on training within the second neural network. The device may also include a reciprocal feed back connection from the output of the second neural network to the first neural network to further influence and change what takes place in the aforesaid neural network.

Abstract: A method for speeding up the convergence of the back-propagation algorithm applied to realize the learning process in a neural network of the multilayer perceptron type intended for instance to recognize a set of samples. The method comprises a first stage based upon the elementary concept of progressively increasing the capability for learning of the network by progressively adding new samples as they are recognized by the network to a starting set of learning samples; a second stage based upon the concept of progressively increasing the learning capabilities of the network by progressively adding not previously recognized samples; and a third stage based upon the concept of progressively increasing the learning capabilities of the network by progressive corruption in the meaning of the assimilation between recognized samples and not recognized samples and their subsequent exposure to the network.

Abstract: Constructing and simulating artificial neural networks and components thereof within a spreadsheet environment results in user friendly neural networks which do not require algorithmic based software in order to train or operate. Such neural networks can be easily cascaded to form complex neural networks and neural network systems, including neural networks capable of self-organizing so as to self-train within a spreadsheet, neural networks which train simultaneously within a spreadsheet, and neural networks capable of autonomously moving, monitoring, analyzing, and altering data within a spreadsheet. Neural networks can also be cascaded together in self training neural network form to achieve a device prototyping system.

Abstract: A multiblock robot system for the logistic and energy supply of electro vehicles, composed of an E-pool net, a Distributed Electrical Vehicle Battery Exchange Network of E-stops, of Distributed Electric Vehicle Battery Exchange Stations, for electro vehicles with control post units and checkcard reader units, approximation sensor units, remote control antenna units, self operating battery chargers with column and below ground coupler units, self operating below ground battery changers. The electro vehicles provided with E-stop compatible sensor, control, coupling and battery units for A multiblock robot system for the logistic and energy supply of electro vehicles, composed of a self operating coupling on the E-stops. E-pool net electro vehicles controlled by E-pool net user checkcards for a multitude of users, controlling all door locking units with code controlled verification of access justification.

Abstract: A system which processes information to identify product choices within a product domain for a user, presents structured data concerning attributes of products in the product domain to the user in a readily understandable and efficient manner, allowing the user to make the best choice according to his or her own personal profile. A user interface presents a sequence of input prompts to the user to gather preference and requirement data for a plurality of attributes of products in the product domain. A decision engine is coupled to the user interface and filters the product domain to present a set of products according to the gathered preference and requirement data as product choices to the user. The preference data comprises a variable associated with particular attributes specified by the user to have a degree of relevance to a product choice in the product domain but not an absolute requirement.

Abstract: A processor provides trace synchronization information to ensure that address information for reconstructing instruction execution flow is provided in trace records with sufficient frequency. A trace record is provided for instructions that change the program flow such as conditional branches. However, target address information is not provided in the trace record for such instructions as conditional branches, only an indication of whether the branch was taken. Target address information is provided, however, for those instructions in which the target address is in some way data dependent. The processor determines whether each trace record includes address information. Each trace entry providing address information causes a counter to be reloaded to a predetermined value which is the desired maximum number of trace records generated before current program address information is provided. The counter counts each trace record produced which does not include address information.