HIERARCHICAL COMPUTING MODULES FOR PERFORMING RECOGNITION USING SPATIAL DISTANCE AND TEMPORAL SEQUENCES
Patent №
US 7,613,675
Granted
2009-11-03
Filed 2007
Owner
NUMENTA, INC.
Lab
—
AI components
5
ml · vision · kr · planning · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
11622457
A hierarchy of computing modules is configured to learn a cause of input data sensed over space and time, and is further configured to determine a cause of novel sensed input data dependent on the learned cause. The hierarchy is further configured to associate a first pattern in the input data and a second pattern in the input data to a same possible cause of the input data.
Machine learningVisionKnowledge representationPlanningAI hardwareG06N 3/08G06N 3/04G06N 3/045G06N 3/047G06N 3/049G06N 3/082G06N 5/02G06N 7/01+1 more
AI classification
AI hardware1.00
Machine learning1.00
Planning1.00
Knowledge representation0.95
Vision0.83
Speech0.02
Evolutionary computation0.01
Natural language0.01
Ownership
NUMENTA, INC.
assignment · 191230060
Assignors
HAWKINS, JEFFREY, GEORGE, DILEEP
On an employer assignment, the assignors are typically the inventors.
From the same owner
HARDWARE ARCHITECTURE FOR INTRODUCING ACTIVATION SPARSITY IN NEURAL NETWORKUS 12,585,928 · 2026HARDWARE ARCHITECTURE FOR PROCESSING DATA IN SPARSE NEURAL NETWORKUS 12,443,835 · 2025Displacement Processor For Inferencing And Learning Based On Sensorimotor Input DataUS 12,361,303 · 2025Performing Inference And Training Using Sparse Neural NetworkUS 12,260,337 · 2025Location Processor for Inferencing and Learning Based on Sensorimotor Input DataUS 12,254,409 · 2025INFERENCING AND LEARNING BASED ON SENSORIMOTOR INPUT DATAUS 12,093,843 · 2024TEMPORAL PROCESSING SCHEME AND SENSORIMOTOR INFORMATION PROCESSINGUS 12,093,847 · 2024INFERENCING AND LEARNING BASED ON SENSORIMOTOR INPUT DATAUS 12,094,192 · 2024