NEURAL NETWORK WITH SEMI-LOCALIZED NON-LINEAR MAPPING OF THE INPUT SPACE

Patent №

US 5,113,483

Granted

1992-05-12

Filed 1990

Owner

MICROELECTRONICS AND COMPUTER TECHNOLOGY CORPORATION

Lab

—

AI components

ml · vision · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

07538833

A neural network includes an input layer comprising a plurality of input units (24) interconnected to a hidden layer with a plurality of hidden units (26) disposed therein through an interconnection matrix (28). Each of the hidden units (26) is a single output that is connected to output units (32) in an output layer through an interconnection matrix (30). Each of the interconnections between one of the hidden units (26) to one of the output units (32) has a weight associated therewith. Each of the hidden units (26) has an activation in the i'th dimension and extending across all the other dimensions in a non-localized manner in accordance with the following equation: ##EQU1## that the network learns by the Back Propagation method to vary the output weights and the parameters of the activation function .mu..sub.hi and .sigma..sub.hi.

Machine learning Vision Planning AI hardwareG06N 3/04G06N 3/0495G06N 3/0499G06N 3/09G06V 10/454

Google Patents

AI classification

Machine learning1.00

AI hardware1.00

Planning0.90

Vision0.58

Evolutionary computation0.12

Speech0.01

Knowledge representation0.00

Natural language0.00

Ownership

MICROELECTRONICS AND COMPUTER TECHNOLOGY CORPORATION

assignment · 53500176

Assignors

KEELER, JAMES D., HARTMAN, ERIC J.

On an employer assignment, the assignors are typically the inventors.

From the same owner

ELECTRICAL INTERCONNECT DEVICE WITH CUSTOMIZEABLE SURFACE LAYER AND INTERWOVEN SIGNAL LINESUS 5,544,018 · 1996 PATTERN RECOGNITION NEURAL NETWORK WITH SACCADE-LIKE OPERATIONUS 5,500,905 · 1996 ATTRIBUTE-ENHANCED SCROLL BAR SYSTEM AND METHODUS 5,479,600 · 1995 COMPUTER SCALABLE VISUALIZATION SYSTEMUS 5,321,505 · 1994 JJ-MOS READ ACCESS CIRCUIT FOR MOS MEMORYUS 5,253,199 · 1993 NEURAL-NETWORK CONTENT-ADDRESSABLE MEMORYUS 5,253,328 · 1993 AUTOMATED INTERCONNECT ROUTING SYSTEMUS 5,187,671 · 1993 METHOD AND SYSTEM FOR GENERATING DYNAMIC INTERACTIVE VISUAL REPRESENTATIONS OF INFORMATION STRUCTURES WITHIN A COMPUTERUS 5,021,976 · 1991

Cited by (75)

CONTROL DEVICE OF VEHICLE DRIVE DEVICE, VEHICLE-MOUNTED ELECTRONIC CONTROL UNIT, TRAINED MODEL, MACHINE LEARNING SYSTEM, METHOD OF CONTROLLING VEHICLE DRIVE DEVICE, METHOD OF PRODUCING ELECTRONIC CONTROL UNIT, AND OUTPUT PARAMETER CALCULATION DEVICEUS 11,732,664 · 2023 Residual-Based Monitoring of Human HealthUS 10,722,179 · 2020 SYSTEMS AND METHODS FOR IMPROVING ACCURACY IN MEDIA ASSET RECOMMENDATION MODELSUS 10,575,057 · 2020 SYSTEMS AND METHODS FOR IMPROVING ACCURACY IN MEDIA ASSET RECOMMENDATION MODELS BASED ON USERS' LEVELS OF ENJOYMENT WITH RESPECT TO MEDIA ASSETSUS 10,003,836 · 2018 Residual-Based Monitoring of Human HealthUS 9,743,888 · 2017 RESIDUAL-BASED MONITORING OF HUMAN HEALTHUS 8,795,170 · 2014 Residual-Based Monitoring of Human HealthUS 8,597,185 · 2013 NON-PARAMETRIC MODELING APPARATUS AND METHOD FOR CLASSIFICATION, ESPECIALLY OF ACTIVITY STATEUS 8,478,542 · 2013 KNOWLEDGE EXTRACTION AND PREDICTIONUS 8,332,348 · 2012 ROBUST DISTANCE MEASURES FOR ON-LINE MONITORINGUS 8,311,774 · 2012 KERNEL-BASED METHOD FOR DETECTING BOILER TUBE LEAKSUS 8,275,577 · 2012 COMPLEX SIGNAL DECOMPOSITION AND MODELINGUS 8,239,170 · 2012 VIEWING MULTI-DIMENSIONAL DATA THROUGH HIERARCHICAL VISUALIZATIONUS 7,777,743 · 2010 SYSTEM FOR EXTRACTION OF REPRESENTATIVE DATA FOR TRAINING OF ADAPTIVE PROCESS MONITORING EQUIPMENTUS 7,739,096 · 2010 PROCESSING MIXED NUMERIC AND SYMBOLIC DATA ENCODINGS USING SCALING AT ONE DISTANCE OF AT LEAST ONE DIMENSION, CLUSTERING, AND A SIGNPOST TRANSFORMATIONUS 7,716,148 · 2010 DIAGNOSTIC SYSTEMS AND METHODS FOR PREDICTIVE CONDITION MONITORINGUS 7,539,597 · 2009 METHOD AND APPARATUS FOR DISCOVERING EVOLUTIONARY CHANGES WITHIN A SYSTEMUS 7,533,006 · 2009 AUTOMATIC NEURAL-NET MODEL GENERATION AND MAINTENANCEUS 7,483,868 · 2009 AUTOMATIC MODEL MAINTENANCE THROUGH LOCAL NETSUS 7,444,310 · 2008 PREDICTIVE EMISSIONS MONITORING METHODUS 7,421,348 · 2008 COMPLEX SIGNAL DECOMPOSITION AND MODELINGUS 7,409,320 · 2008 USING NEURAL NETWORKS FOR DATA MININGUS 7,321,879 · 2008 HIERARCHICAL DETERMINATION OF FEATURE RELEVANCYUS 7,313,279 · 2007 SELF-ORGANIZING DATA DRIVEN LEARNING HARDWARE WITH LOCAL INTERCONNECTIONSUS 7,293,002 · 2007 ADAPTIVE MODELING OF CHANGED STATES IN PREDICTIVE CONDITION MONITORINGUS 7,233,886 · 2007

and 50 more

Related research

Learning Neural Representations and Local Embedding for Nonlinear Dimensionality MappingOpenAlex Learning Neural Representations and Local Embedding for Nonlinear Dimensionality Reduction MappingOpenAlex Deep Mapping Algorithm for More Effective Neural Network TrainingOpenAlex Nonlinear dynamics of localization in neural receptive fieldsarXiv Dynamic Block-Wise Local Learning Algorithm for Efficient Neural Network TrainingSemantic Scholar

Full text

Google Patents