Abstract: A system and method for enhancing knowledge discovery from data using a learning machine in general and a support vector machine in particular in a distributed network environment. A customer may transmit training data, test data and live data to a vendor's server from a remote source, via a distributed network. The customer may also transmit to the server identification information such as a user name, a password and a financial account identifier. The training data, test data and live data may be stored in a storage device. Training data may then be pre-processed in order to add meaning thereto. Pre-processing data may involve transforming the data points and/or expanding the data points. By adding meaning to the data, the learning machine is provided with a greater amount of information for processing. With regard to support vector machines in particular, the greater the amount of information that is processed, the better generalizations about the data that may be derived.

Abstract: A user authentication apparatus for use in controlling access to a system inputs an owner's login name and password and then extracts the owner's timing vectors from keystroke characteristics with which the owner repeatedly types the owner's password to thereby form a training set. A neural network is trained by using each of the owner's timing vectors in the training set as an input. Thereafter, when a user inputs the owner's login name and password, it is checked if the user's password is identical to the owner's password. The user's timing vector is extracted from a keystroke characteristic to type the user's password if the checked result is affirmative, and the user is prohibited from accessing the system if otherwise. The user's timing vector is applied to the trained neural network as an input and a difference between the input and an output of the neural network is compared with a predetermined threshold.

Abstract: A recognition apparatus and method using a neural network is provided. A neuron-like element stores a value of its inner condition. The neuron-like element also updates a values of its internal status on the basis of an output from the neuron-like element itself, outputs from other neuron-like elements and an external input, and an output value generator a value of its internal status into an external output. Accordingly, the neuron-like element itself can retain the history of input data. This enables the time series data, such as speech, to be processed without providing any special devices in the neural network.

Abstract: An artificial neuron, which may be implemented either in hardware or software, has only one significant processing element in the form of a multiplier. Inputs are first fed through gating functions to produce gated inputs. These gated inputs are then multiplied together to produce a product which is multiplied by a weight to produce the neuron output.

Abstract: A malfunction diagnostic and repair guidance system and method wherein a matrix of numbers indicating the state of a complex binary system is used as an input vector for a neural network pattern processing capability that is focused to distinguish malfunction types of patterns. The neural network capability provides two complementary network types to classify and generalize the binary matrix. An interactive operator interface is updated with each repair after the root cause and is proposed repair of a malfunction is identified.

Abstract: Classifiers (110) and a comparator (112) perform an identification method (400) to identify a class as one of a predetermined set of classes. The identification method is based on determining the observation costs associated with the unidentified class. The identification method includes combining models representing the predetermined set of classes and the unidentified vectors representing the class. The predetermined class associated with the largest observation cost is identified as the class. Additionally, a unique, low-complexity training method (300) includes creating the models which represent the predetermined set of classes.

Abstract: A system and method for enhancing knowledge discovery from data using multiple learning machines in general and multiple support vector machines in particular. Training data for a learning machine is pre-processed in order to add meaning thereto. Pre-processing data may involve transforming the data points and/or expanding the data points. By adding meaning to the data, the learning machine is provided with a greater amount of information for processing. With regard to support vector machines in particular, the greater the amount of information that is processed, the better generalizations about the data that may be derived. Multiple support vector machines, each comprising distinct kernels, are trained with the pre-processed training data and are tested with test data that is pre-processed in the same manner. The test outputs from multiple support vector machines are compared in order to determine which of the test outputs if any represents a optimal solution.

Abstract: A system and process for readily determining, for a specified knowledge domain in a given field of endeavor, perturbations applicable to an artificial neural network embodying such a specified knowledge domain that will produce a desired output, comprising a first, previously trained, artificial neural network containing training in some problem domain, which neural network is responsive to the presentment of a set of data inputs at the input portion thereof to produce a set of data outputs at the output portion thereof, a monitoring portion which constantly monitors the outputs of the first neural network to identify the desired outputs, and a network perturbation portion for effecting the application of perturbations, either externally or internally, to the first neural network to thereby effect changes in the output thereof.

Abstract: A recursive neural net including processing elements (1) each having a linear saturated function as an input/output function. The elements (1) are divided into a plurality of blocks (2), and the states of the elements (1) are asynchronously updated block by block while being synchronously updated within each block (2). Since convergence is ensured for any symmetric synaptic matrix (W) by selecting a step-size for each particular problem, the neural net can be applied to any optimization problem. In addition, a neural net system is composed of an optical computing unit (201 to 205) performing a vector matrix calculation using light, a threshold processing unit (206) performing a threshold processing operation, a coefficient multiplying unit (209) performing a step-size processing operation, a saturated linear computing unit (207) performing a saturated linear function operation, and a block control unit (208) performing selection of a block to be updated and state updating therefor.

Abstract: A neural network includes a monitor circuit for monitoring an output value of each neuron and a weighting calculation circuit for calculating a weighting between neurons in accordance with designation from the monitor circuit in order to determine the weightings between the neurons in accordance with an energy function expressed in the form of a sum of a constrain condition and an evaluation function. The monitor circuit monitors the output values of the neurons and transmits, to the weighting calculation circuit, information representing an unsatisfactory state in which a distribution of the output values does not satisfy the constrain condition. The weighting calculation circuit changes the weightings between the neurons, e.g., doubles the weightings, every time it receives this information.

Abstract: A digital electronics system, such as a computer, includes circuits which provides signals proportional to the instantaneous voltage and current on the power bus to a microprocessor. The microprocessor uses these signals, the capacitance of the system filter capacitors, and the desired time for the system voltage to remain above a minimum voltage, to calculate an instantaneous voltage threshold. When the power bus voltage falls below this threshold voltage, the microprocessor provides a signal warning of impending power failure. The product of the voltage and current, i.e. the instantaneous system power, is displayed on an alphanumeric LED on the front panel of the computer.

Abstract: N neural networks having different set-values are provided, where N is an integer greater than 2. Each neural network has plurality of artificial neurons and processes information. An optimal output detecting circuit receives outputs of the N neural networks and determines the optimal one of the neural networks based on the outputs of the N neural networks. An output circuit receives and outputs the output of the neural network detected by the optimal output detecting circuit.

Abstract: An optimum utilization of the processing power of a data processing system is made possible by information marking a special processing state assigned to those jobs that can be arbitrarily shifted in the time axis. These jobs are performed by the system after activation by a user's input and until such time as a new user's input is carried out.

Abstract: A system includes a computer main body, and an expansion unit detachably connected to the computer main body, for supplying a power to the computer main body and expanding a function of the computer. A power in the expansion unit is consumed in the expansion unit prior to power supply to the computer main body so as to stably supply a power to circuit components of the expansion unit. The expansion unit includes an expansion connector to which at least one expansion board is arbitrarily detachably connected, a power supply for supplying the power to the circuit components including the expansion circuit boards and to the computer main body, and a switch for detecting a power supplied from the power supply to the circuit components and stopping power supply to the computer main body by the power supply when the power exceeds a predetermined value.

Abstract: To reduce the total power consumption of a computer system, a supervisory control method is used to detect a substantial rest state of a CPU wherein it is waiting for a substantial task to start while repeatedly executing a small loop program. The method includes a step addresses accessed by the CPU in a predetermined period of time Ta are stored in proper address blocks, the stored addresses being defined as a learned address, and a step wherein a check is made to see if the CPU accesses an address other than the learned address in a predetermined period of time Tb. When no access of the CPU to any address other than the learned address is detected in the checking step, the both steps are repeated until it is detected in the checking step that an address other than the learned address is accessed by the CPU. In this instance, at least the time Ta is reduced for each repetition of the both steps.

Abstract: An adaptive process control system selectively controls vibrations in a given medium in real time. Unwanted vibrations present at a point being monitored in a given medium are sensed, and the system generates an appropriate offsetting vibration that is applied to the medium at a convenient location, which may be remote from the monitored point. The system includes a vibration sensor, such as one or more accelerometers, that sense both input and output vibrations present within the medium; at least one vibration generator, such as an electromagnetic shaker, that generates appropriate offsetting vibrations that are applied to the medium at one or more appropriate locations; and a neural network controller that controls the vibration generator(s) so as to force the sensed vibration at the monitored point(s) to a desired level. The adaptive vibration cancellation provided by the invention takes place in real time, and without the need to process time-consuming complex mathematical algorithms.

Abstract: A robot apparatus includes a robot arm, a robot hand, an electrical/electronic device mounted on the robot hand for operating the robot hand, and a hand attaching/detaching device, arranged between the robot arm and the robot hand, for detachably mounting the robot hand on the robot arm. A signal transmission path, is connected to an external robot controller at one end thereof and to the electrical/electronic device at the other end thereof, extends through the hand attaching/detaching device, and is able to be disconnected between the robot hand side and the robot arm side in the hand attaching/detaching device.

Abstract: A robot hand apparatus includes a hand base mounted on a shaft extending from the leading end of a robot main body, a rotary base rotatably held by the hand base, an electric contact provided on a contact surface of the hand base, an electric contact ring provided on a rotary contact surface of the rotary base, a plurality of chucks provided on the rotary base, a first signal converting device positioned on the robot main body side, and a second signal converting device positioned on the rotary base side. The first signal converting device converts parallel signals outputted from a robot control section into a serial signal so as to transmit the serial signal to the second signal converting device via contact between the electric contact and the electric contact ring, and converts a serial signal outputted from the second signal converting device into parallel signals so as to transmit the parallel signals to the robot control section.

Abstract: A provides a system and method for managing power in a portable, pen-based notebook computer. The system and method provides a means for minimizing power consumption by collecting and interpreting power related data of various processing elements while hiding many of the details from the end-user. The system monitors, collects, and acts, upon power-related data in a portable computer to maximize the amount of time the portable computer can be used between battery re-charging with minimal user intervention. The system has a plurality of independently controllable power planes and a plurality of central processing units (CPUs) operating asynchronously with respect to each other. The present invention is further comprised of an on/off glue logic means for monitoring battery condition, user invoked functions, and system state and a power management means for controlling the operation of each of the CPUs as a function of the conditions sensed by a sensing means.

Abstract: The neural engine (20) is a hardware implementation of a neural network for use in real-time systems. The neural engine (20) includes a control circuit (26) and one or more multiply/accumulate circuits (28). Each multiply/accumulate circuit (28) includes a parallel/serial arrangement of multiple multiplier/accumulators (84) interconnected with weight storage elements (80) to yield multiple neural weightings and sums in a single clock cycle. A neural processing language is used to program the neural engine (20) through a conventional host personal computer (22). The parallel processing permits very high processing speeds to permit real-time pattern classification capability.