Abstract: A neural network, which may be implemented either in hardware or software, is constructed of neurons or neuron circuits each having only one significant processing element in the form of a multiplier. A hidden neuron in the neural network generates an output based on the product of a plurality of functions. The neural network utilizes a training algorithm which does not require repetitive training and which yields a global minimum to each given set of input vectors.
Abstract: A speech-recognition system for recognizing isolated words includes pre-processing circuitry for performing analog-to-digital conversion and cepstral analysis, and a plurality of neural networks which compute discriminant functions based on polynomial expansions. The system may be implemented using either hardware or software or a combination thereof. The speech wave-form of a spoken word is analyzed and converted into a sequence of data frames. The sequence of frames is partitioned into data blocks, and the data blocks are then broadcast to a plurality of neural networks. Using the data blocks, the neural networks compute polynomial expansions. The output of the neural networks is used to determine the identity of the spoken word. The neural networks utilize a matrix-inversion or alternatively a least-squares estimation training algorithm which does not require repetitive training and which yields a global minimum to each given set of training examples.
Abstract: A method and apparatus for creating a filtration knowledge base is used in a filtration process for separating a liquid component and a solid component from a slurry. The concentrations of the solid component in the slurry, and of the solid component in the separated liquid, are monitored and stored in a knowledge base along with a quantity relating to the amount of filtering. The knowledge base can be used for controlling the slurry-producing process, routing the separated liquid, automated billing and automated compliance reporting.
Abstract: A wide-angle lens produces a distorted wide-angle optical image. An imaging sensor, having a surface in optical communication with the wide-angle lens, converts the wide-angle optical image into a corresponding output signal. The imaging sensor includes a plurality of imaging elements. The plurality of imaging elements have a distribution on the surface of the sensor that is representable by a nonlinear function, wherein the distribution of the imaging elements corrects the distortion in the wide-angle image.
Type:
Grant
Filed:
December 8, 1994
Date of Patent:
February 6, 1996
Assignee:
Motorola, Inc.
Inventors:
Charles P. Richardson, Bruce E. Stuckman
Abstract: Neural networks learn expert system rules, for either business or real-time applications, to improve the robustness and speed of execution of the expert system. One or more neural networks are constructed which incorporate the production rules of one or more expert systems. Each neural network is constructed of neurons or neuron circuits each having only one significant processing element in the form of a multiplier. Each neural network utilizes a training algorithm which does not require repetitive training and which yields a global minimum to each given set of input vectors.
Abstract: A technique for converting an existing expert system into one incorporating one or more neural networks includes the steps of separating the knowledge base and inference engine of the existing expert system, identifying the external and internal inputs and outputs, identifying subsystems from the inputs and outputs, using a neural network for each subsystem, training each neural network to learn the production rules of its associated subsystem, and computing exact or interpolated outputs from a given set of inputs. Each neural network utilizes a training algorithm which does not require repetitive training and which yields a global minimum to each given set of inputs.
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.