METHOD AND APPARATUS FOR PARTITIONING HIGH-DIMENSION VECTORS FOR USE IN A MASSIVE INDEX TREE
Patent №
US 8,185,531
Granted
2012-05-22
Filed 2009
Owner
NAHAVA INC.
Lab
—
AI components
2
vision · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
12507271
A method and apparatus for partitioning high-dimension vectors for use in a massive index have been disclosed. Using an initial guess on a collection of vectors, the vectors are examined. If the collection is not empty then dividing the collection until a collection contains a single vector or contains two vectors then transforming the two vectors into a majorize result and transforming the result into a graphical representation for a user.
AI classification
Vision1.00
AI hardware0.83
Knowledge representation0.48
Machine learning0.25
Speech0.00
Planning0.00
Evolutionary computation0.00
Natural language0.00
Ownership
NAHAVA INC.
assignment · 229890400
Assignors
NAKANO, RUSSELL T
On an employer assignment, the assignors are typically the inventors.
From the same owner
METHOD AND APPARATUS FOR CACHED ADAPTIVE TRANSFORMS FOR COMPRESSING DATA STREAMS, COMPUTING SIMILARITY, AND RECOGNIZING PATTERNSUS 7,664,173 · 2010METHOD AND SYSTEM FOR EFFICIENT INDEXED STORAGE FOR UNSTRUCTURED CONTENTUS 7,650,320 · 2010METHOD AND APPARATUS FOR FAST SIMILARITY-BASED QUERY, SELF-JOIN, AND JOIN FOR MASSIVE, HIGH-DIMENSION DATASETSUS 7,644,090 · 2010METHOD AND APPARATUS FOR FUNDAMENTAL OPERATIONS ON TOKEN SEQUENCES: COMPUTING SIMILARITY, EXTRACTING TERM VALUES, AND SEARCHING EFFICIENTLYUS 7,421,418 · 2008