Abstract: Concurrent tradeoff analysis (10) first ascertains a set of constraints (16) and variables (18) for specifying a solution, and then defines characteristics for specifying the merit of the solution. Computations are made to determine the values for the variables (18) and characteristics, which represent a current solution state. The current solution state is checked (42) to ensure that there are no violations of the constraints (16). If a violation exists, one or more alternatives are generated (46) via a number of methods, and the alternatives are evaluated (48) along with the current solution state. One or more most promising alternative is chosen, and the process proceeds until values for all of the variables (18) and characteristics are computed.

Abstract: One or more machine code entities such as functions are created which represent solutions to a problem and are directly executable by a computer. The programs are created and altered by a program in a higher level language such as "C" which is not directly executable, but requires translation into executable machine code through compilation, interpretation, translation, etc. The entities are initially created as an integer array that can be altered by the program as data, and are executed by the program by recasting a pointer to the array as a function type. The entities are evaluated by executing them with training data as inputs, and calculating fitnesses based on a predetermined criterion. The entities are then altered based on their fitnesses using a machine learning algorithm by recasting the pointer to the array as a data (e.g. integer) type. This process is iteratively repeated until an end criterion is reached.

Abstract: An authoring system and method create a knowledge base for an expert system that comprises communication cells for storing external data, assertion cells for storing data acquired from a user in the course of a user dialog, and interaction cells that specify (multimedia) interactions with the user, which are carried out as the cells are invoked by the run-time program. Each interaction cell has an enabling condition that must be satisfied before it can be invoked. At authoring time, the knowledge base is constructed by an expert system author who allocates the knowledge base cells on a rectangular grid similar to a spreadsheet. The author can try out various what-if scenarios by setting the values of assertion and communication cells and recalculating the knowledge base or simulating the created expert system. The grid is only an authoring tool, which is not visible or present at run time.

Abstract: A method and apparatus for assisting a user in completing a task through the asking of questions about the task and providing answer choices to the questions for the user. The method includes storing a set of question procedures which include a reference to another procedure and storing answer procedures for the question procedures, which also include references to other procedures.Questions are dynamically generated by executing a question procedure which, in turn, calls a referenced procedure to generate a result based on one or more previous answers by the user. The referenced procedure passes the result to the questions procedure for use in generating the question. The same process is used for dynamically generating answer choices for the questions. The referenced procedures may include, among others, fetches of previous answers, conditional statements that choose among possible results based on a previous answer, or references to still other procedures.

Abstract: An RTA or similar rule-based agent (102) is enabled to construct a virtual simulation of its environment by the provision of an internal prediction module (100). The prediction module comprises a rule population run in tandem with the population (106) defining the agent behaviors. The prediction module rules represent predictions of agent behavior state changes and their accuracy is periodically checked (110), with more accurate rules being assigned a higher fitness rating. A genetic algorithm (108) defines mutation operators by which further rules are evolved from those having the highest fitness. When a predetermined level of fitness (prediction accuracy) is achieved, the prediction module rules provide (116) a virtual simulation of the environment to the agent behaviors by direct control in place of external (real world) stimuli.

Abstract: A system and method for automatically detecting fires in select areas, and reacting thereto to put out the fires. A stationary, earth orbit satellite, pilotless drone aircrafts or piloted aircraft contains one or more infrared detectors and optical means for detecting small fires when they first occur in fields and wooded areas, preferably where man made campfires and trash dumping are prohibited. A computer in the satellite, drone or piloted aircraft and/or on the ground receives and analyzes image signals of the earth area or areas being monitored and, upon detecting infrared radiation of varying intensity and variable shape, indicative that a fire has started, generates coded signals which are (a) indicative of the coordinate locations of the fire, (b) the extent of the fire, (c) the shape of the area(s) burning, (d) the direction of movement of the fires (e) the speed(s) of the flame fronts, (f) smoke condition, (g) intensity of the fire, (h) fire ball location(s), etc.

Abstract: A recurrent, neural network-based fuzzy logic system includes in a rule base layer and a membership function layer neurons which each have a recurrent architecture with an output-to-input feedback path including a time delay element and a neural weight. Further included is a recurrent, neural network-based fuzzy logic rule generator wherein a neural network receives and fuzzifies input data and provides data corresponding to fuzzy logic membership functions and recurrent fuzzy logic rules.

Abstract: A rules base according to the invention comprises multiple entries encoded in a storage medium, e.g., optical disk, magnetic disk, or read-only memory or random access memory. Each entry is encoded to include, or is otherwise associated with, an objective and with a circumstance. Each entry is also marked to reflect its respective status, e.g., via status fields encoded in the records. These statuses include, inter alia, "valid," reflecting that information encoded in, or otherwise associated with, the entry corresponds to a rule for corresponding objective/circumstance; "inheritance," reflecting that the rule for the corresponding objective/circumstance is to be sought elsewhere, e.g., in another entry in the rules base; and "invalid," reflecting that the corresponding combination of objective and circumstance is invalid. The rules base also includes an "inheritance" structure that, too, is encoded in a storage medium.

Abstract: A dynamically stable associative learning neural system includes a plurality of neural network architectural units. A neural network architectural unit has as input both condition stimuli and unconditioned stimulus, an output neuron for accepting the input, and patch elements interposed between each input and the output neuron. The patches in the architectural unit can be modified and added. A neural network can be formed from a single unit, a layer of units, or multiple layers of units.

Abstract: A device comprising invertor circuit group including two or more invertor circuits formed by neuron MOS transistors; means for applying a first signal voltage common to the two or more invertors of the invertor circuit group to a first input gate of the invertor circuit; means for applying a given second signal to one or more second input gates other than the first input gate of the invertor circuits; a delay circuit for transmitting the variation of the output voltage of at least one of the invertor circuits of the invertor circuit group with a time delay generated by used of the variation with time of the signal voltage of either or both of the first and second signal voltages; a transistor whose ON and OFF is controlled by the signal transmitted from the delay circuit; storage circuits taking in signals by the ON and OFF of the transistor; and means for executing a given logical operation with respect to the output voltage signals generated by the invertor circuit group.

Abstract: A fuzzy operation apparatus which can supply various fuzzy operators by combining basic operators provided by hardware with microprograms, performs fuzzy operations in parallel by connecting a plurality of fuzzy operation portions using a network, and performs parallel defuzzification of the result of fuzzy operations stored in the fuzzy operation portions throughout the network. The present invention establishes a network between fuzzy operation portions, performs fuzzy operation in parallel at a plurality of fuzzy operation portions, and defuzzifies each element of a fuzzy set dispersed and stored in the fuzzy operation portions such that defuzzification speed is fast. Also, since there is no need for an exclusive defuzzification processor, the cost of the system is low.

Abstract: The present invention relates to a discourse manager which permits effective collaboration between a user and a computer agent. The system operates according to a theory of collaborative discourse between humans, with the computer agent playing the same role as a human collaborator. The present invention does not concern the internal operation of a particular agent, but relates rather to the structures for managing a collaborative discourse between any type of agent and the user. The discourse manager includes a memory in which application-specific recipes are stored and a memory in which the discourse state is stored. Each recipe specifies a set of actions or subtasks which are performed to achieve an objective. The discourse state includes structures to track the agent's and user's current objectives, a selected recipe for each objective, and completed steps in each recipe.

Abstract: A method and apparatus for classifying an input as belonging to one of a plurality of predefined classes, comprises: (a) developing a plurality of feature values and forming a feature vector from the feature values which is representative of the input, (b) applying the feature vector to a knowledge-base comprising predictivity curves for each class of said plurality of classes, and developing a plurality of predictivity values for each feature, each predictivity value being indicative of a likelihood of the input belonging to a respective one of each of said classes based on the feature value; (c) combining the predictivity values developed for each of the features for each class to generate a total predictivity value for each class; and (d) generating a determination of class based upon the total predictivity values generated by the prior step.

Abstract: A persuasion organizer and calculator with which attorneys and others required to form and develop persuasive arguments may create, modify, and control a knowledge base and a persuasive calculus without the need for a knowledge engineer. By eliminating the knowledge engineer from the process of creating and maintaining a knowledge base, the present invention minimizes the problems of ambiguity and confusion found in the prior art. The present invention provides a structure for litigators that allows simple, non-expert creation and modification of decisional frameworks, objective and subjective probabilities, and standards of proof. Furthermore, the present invention allows the user to analyze the elements of a persuasive argument (including matters, issues, facts, laws, evidence, witnesses, and the like) to predict the strength of such an argument and determine elements which may require additional support and resource allocation.

Abstract: A system for computing an affinity for relocating a cell on a surface of a semiconductor chip is disclosed herein. The cell is located within a region and belongs to a net of cells. The system initially computes a weight associated with all cells in the net. The sytem then sums the weights of all cells in the net containing the cell for all cells located inside the region and at positions greater than and less than edges of the region and computes the affinity for moving the cell to points on the surface greater than, equal to, and less than the current position of the cell based on the weight sums from said summing function. The computing function further comprises combining the affinities determined based on weight sums with other affinities. The summing function further comprises computing a relationship between the amount of rows and columns of regions on the semiconductor chip surface, and the affinity computation function comprises combining the relationship with the weight sums.

Abstract: A method for determining a stowage plan is proposed which utilizes "genetic" or "evolutionary" search techniques. The method includes the steps of generating a multiplicity of "genotypes", each of which corresponds to one possible stowage plan. Each stowage plan is then evaluated in terms of the cost of implementing it. The cost is at least a function of the weight distribution of the vessel and the number of restows required. The initial genotypes and the cost function for evaluating them are provided to the genetic algorithm which operates to reduce the cost to one below a predefined threshold.

Abstract: An apparatus and method for a user to program a personal software agent using an agent manager. The agent manager receives instructions for creating a rule. The rule is placed in a hierarchical order. A determination is made as to whether the rule is valid within the hierarchical order. If the rule is not valid, repairs are suggested to make the rule valid.

Abstract: In a computer system, a user interacts with a plurality of applications using natural language text provided by an input device. In order to enable the applications for user interaction, rules are registered on a blackboard of an arbiter. The arbiter can be localized, or distributed. Each rule is identified with a particular application, and can include a callback procedure. Each rule includes a left-hand side symbol and a right-hand side string which is a translation of the symbol. A parser parses a natural language input text string using the register rules to generate an evaluation tree. The evaluation tree is expressed in the form of an interpretive language. The evaluation tree is interpreted to produce at least one application request. The application request is generated by the callback procedure associated with a specific one of the rules applied during the parsing of the input text. The request is transmitted to the application identified with the applied rule.

Abstract: A flexible, event driven and conditional rule based mail messaging system which can be transparently implemented for use in electronic mail applications. A rule mechanism is implemented having a "When-If-Then" event-driven, conditional, action-invoking paradigm or "triplet" which permits definition of a repertoire of events considered to be significant events upon which to trigger actions in the electronic mail messaging system. Each particular event may be associated with a specific mail message and/or rules to promote efficient mapping of messages, events and rules so that only rules associated with a specific event are invoked upon occurrence of the event. Only relevant rules, i.e. those associated with a satisfied event, need be further processed. A graphical user interface to a structured rule editor facilitates synthesis of rules by a user via a substantially transparent rule engine.

Abstract: The invention is an autonomous adaptive agent which can learn verbal as well as nonverbal behavior. The primary object of the system is to optimize a primary value function over time through continuously learning how to behave in an environment (which may be physical or electronic). Inputs may include verbal advice or information from sources of varying reliability as well as direct or preprocessed environmental inputs. Desired agent behavior may include motor actions and verbal behavior which may constitute a system output and which may also function "internally" to guide external actions. A further aspect of the invention is an efficient "training" process by which the agent can be taught to utilize verbal advice and information along with environmental inputs.