US 12,094,192 B2
Inferencing and learning based on sensorimotor input data
Jeffrey C. Hawkins, Atherton, CA (US); and Subutai Ahmad, Palo Alto, CA (US)
Assigned to Numenta, Inc., Redwood City, CA (US)
Filed by Numenta, Inc., Redwood City, CA (US)
Filed on Jul. 20, 2021, as Appl. No. 17/380,639.
Application 17/380,639 is a continuation of application No. 16/268,148, filed on Feb. 5, 2019, granted, now 11,100,414.
Application 16/268,148 is a continuation in part of application No. 15/594,077, filed on May 12, 2017, granted, now 10,977,566.
Claims priority of provisional application 62/335,995, filed on May 13, 2016.
Prior Publication US 2021/0374578 A1, Dec. 2, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 5/04 (2023.01); G06F 18/25 (2023.01); G06K 9/00 (2022.01); G06K 9/62 (2022.01); G06N 3/04 (2023.01); G06N 3/063 (2023.01); G06N 5/045 (2023.01); G06N 5/046 (2023.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01); G06V 10/94 (2022.01)
CPC G06V 10/82 (2022.01) [G06F 18/251 (2023.01); G06N 3/04 (2013.01); G06N 3/063 (2013.01); G06N 5/045 (2013.01); G06N 5/046 (2013.01); G06V 10/803 (2022.01); G06V 10/95 (2022.01); G06V 10/955 (2022.01); G05B 2219/40053 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method of performing inference using a plurality of multi-layer systems corresponding to a plurality of nodes, the method comprising:
generating, by a first inference system of a first multi-layer system of a first node, a first input representation by at least processing first sensory input indicating a first set of candidate pairs, the first set of candidate pairs indicating detection of a first feature of an unidentified object at first candidate locations on the unidentified object associated with the first feature;
determining, by the first inference system, a first output representation corresponding to the first input representation by processing the first input representation, the first output representation indicating a first set of candidate objects associated with the first set of candidate pairs;
sending an inter-node signal representing the first output representation from the first inference system to a second inference system;
generating, by the second inference system of a second multi-layer system of a second node, a second input representation by processing second sensory input indicating a second set of candidate pairs, the second set of candidate pairs indicating detection of a second feature of the unidentified object at second candidate locations on the unidentified object associated with the second feature; and
determining, by the second inference system, a second output representation indicating a second set of candidate objects corresponding to the second input representation and consistent with the first output representation based on the inter-node signal from the first inference system.