Patents by Inventor Robert G. Jaros
Robert G. Jaros has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20150227849Abstract: An adaptive pattern recognition system optimizes an invariance objective and an input fidelity objective to accurately recognize input patterns in the presence of arbitrary input transformations. A fixed state or value of a feature output can nonlinearly reconstruct or generate multiple spatially distant input patterns and respond similarly to multiple spatially distant input patterns, while preserving the ability to efficiently evaluate the input fidelity objective. Exemplary networks, including a novel factorization of a third-order Boltzmann machine, exhibit multilayered, unsupervised learning of arbitrary transformations, and learn rich, complex features even in the absence of labeled data.Type: ApplicationFiled: December 7, 2010Publication date: August 13, 2015Applicant: Yahoo! Inc.Inventors: Robert G. Jaros, Simon Kayode Osindero
-
Patent number: 8666917Abstract: 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. At least one of the computing modules has a sequence learner module configured to associate sequences of input data received by the computing module to a set of causes previously learned in the hierarchy.Type: GrantFiled: September 5, 2012Date of Patent: March 4, 2014Assignee: Numenta, Inc.Inventors: Robert G. Jaros, Dileep George, Jeffrey Hawkins, Frank Astier
-
Patent number: 8504494Abstract: A spatio-temporal learning node is a type of HTM node which learns both spatial and temporal groups of sensed input patterns over time. Spatio-temporal learning nodes comprise spatial poolers which are used to determine spatial groups in a set of sensed input patterns. The spatio-temporal learning nodes further comprise temporal poolers which are used to determine groups of sensed input patterns that temporally co-occur. A spatio-temporal learning network is a hierarchical network including a plurality of spatio-temporal learning nodes.Type: GrantFiled: September 7, 2011Date of Patent: August 6, 2013Assignee: Numenta, Inc.Inventors: Robert G. Jaros, Jeffrey L. Edwards, Dileep George, Jeffrey C. Hawkins
-
Patent number: 8407166Abstract: A temporal pooler for a Hierarchical Temporal Memory network is provided. The temporal pooler is capable of storing information about sequences of co-occurrences in a higher-order Markov chain by splitting a co-occurrence into a plurality of sub-occurrences. Each split sub-occurrence may be part of a distinct sequence of co-occurrences. The temporal pooler receives the probability of spatial co-occurrences in training patterns and tallies counts or frequency of transitions from one sub-occurrence to another sub-occurrence in a connectivity matrix. The connectivity matrix is then processed to generate temporal statistics data. The temporal statistics data is provided to an inference engine to perform inference or prediction on input patterns. By storing information related to a higher-order Markov model, the temporal statistics data more accurately reflects long temporal sequences of co-occurrences in the training patterns.Type: GrantFiled: June 12, 2009Date of Patent: March 26, 2013Assignee: Numenta, Inc.Inventors: Jeffrey C. Hawkins, Dileep George, Charles Curry, Frank E. Astier, Anosh Raj, Robert G. Jaros
-
Publication number: 20120330885Abstract: 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. At least one of the computing modules has a sequence learner module configured to associate sequences of input data received by the computing module to a set of causes previously learned in the hierarchy.Type: ApplicationFiled: September 5, 2012Publication date: December 27, 2012Applicant: NUMENTA, INC.Inventors: Robert G. Jaros, Dileep George, Jeffrey Hawkins, Frank Astier
-
Patent number: 8285667Abstract: 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. At least one of the computing modules has a sequence learner module configured to associate sequences of input data received by the computing module to a set of causes previously learned in the hierarchy.Type: GrantFiled: October 9, 2009Date of Patent: October 9, 2012Assignee: Numenta, Inc.Inventors: Robert G. Jaros, Dileep George, Jeffrey C. Hawkins, Frank E. Astier
-
Patent number: 8219507Abstract: A node, a computer program storage medium, and a method for a hierarchical temporal memory (HTM) network where at least one of its nodes generates a top-down message and sends the top-down message to one or more children nodes in the HTM network. The first top-down message represents information about the state of a node and functions as feedback information from a current node to its child node. The node may also maintain history of the input patterns or co-occurrences so that temporal relationships between input patterns or co-occurrences may be taken into account in an inference stage. By providing the top-town message and maintaining history of previous input patterns, the HTM network may, among others, (i) perform more accurate inference based on temporal history, (ii) make predictions, (iii) discriminate between spatial co-occurrences with different temporal histories, (iv) detect “surprising” temporal patterns, (v) generate examples from a category, and (vi) fill in missing or occluded data.Type: GrantFiled: June 26, 2008Date of Patent: July 10, 2012Assignee: Numenta, Inc.Inventors: Robert G. Jaros, Dileep George
-
Patent number: 8121961Abstract: A Hierarchical Temporal Memory (HTM) network has at least first nodes and a second node at a higher level than the first nodes. The second node provides an inter-node feedback signal to the first nodes for grouping patterns and sequences (or co-occurrences) in input data received at the first nodes at the first nodes. The second node collects forward signals from the first nodes; and thus, the second node has information about the grouping of the patterns and sequences (or co-occurrences) at the first nodes. The second node provides inter-node feedback signals to the first nodes based on which the first nodes may perform the grouping of the patterns and sequences (or co-occurrences) at the first nodes.Type: GrantFiled: June 2, 2011Date of Patent: February 21, 2012Assignee: Numenta, Inc.Inventors: Dileep George, Robert G. Jaros
-
Publication number: 20120005134Abstract: A spatio-temporal learning node is a type of HTM node which learns both spatial and temporal groups of sensed input patterns over time. Spatio-temporal learning nodes comprise spatial poolers which are used to determine spatial groups in a set of sensed input patterns. The spatio-temporal learning nodes further comprise temporal poolers which are used to determine groups of sensed input patterns that temporally co-occur. A spatio-temporal learning network is a hierarchical network including a plurality of spatio-temporal learning nodes.Type: ApplicationFiled: September 7, 2011Publication date: January 5, 2012Applicant: Numenta, Inc.Inventors: Robert G. Jaros, Jeffrey L. Edwards, Dileep George, Jeffrey C. Hawkins
-
Patent number: 8037010Abstract: A spatio-temporal learning node is a type of HTM node which learns both spatial and temporal groups of sensed input patterns over time. Spatio-temporal learning nodes comprise spatial poolers which are used to determine spatial groups in a set of sensed input patterns. The spatio-temporal learning nodes further comprise temporal poolers which are used to determine groups of sensed input patterns that temporally co-occur. A spatio-temporal learning network is a hierarchical network including a plurality of spatio-temporal learning nodes.Type: GrantFiled: February 28, 2008Date of Patent: October 11, 2011Assignee: Numenta, Inc.Inventors: Robert G. Jaros, Jeffrey L. Edwards, Dileep George, Jeffrey C. Hawkins
-
Publication number: 20110231351Abstract: A Hierarchical Temporal Memory (HTM) network has at least first nodes and a second node at a higher level than the first nodes. The second node provides an inter-node feedback signal to the first nodes for grouping patterns and sequences (or co-occurrences) in input data received at the first nodes at the first nodes. The second node collects forward signals from the first nodes; and thus, the second node has information about the grouping of the patterns and sequences (or co-occurrences) at the first nodes. The second node provides inter-node feedback signals to the first nodes based on which the first nodes may perform the grouping of the patterns and sequences (or co-occurrences) at the first nodes.Type: ApplicationFiled: June 2, 2011Publication date: September 22, 2011Applicant: NUMENTA, INC.Inventors: Dileep George, Robert G. Jaros
-
Patent number: 7983998Abstract: A Hierarchical Temporal Memory (HTM) network has at least first nodes and a second node at a higher level than the first nodes. The second node provides an inter-node feedback signal to the first nodes for grouping patterns and sequences (or co-occurrences) in input data received at the first nodes at the first nodes. The second node collects forward signals from the first nodes; and thus, the second node has information about the grouping of the patterns and sequences (or co-occurrences) at the first nodes. The second node provides inter-node feedback signals to the first nodes based on which the first nodes may perform the grouping of the patterns and sequences (or co-occurrences) at the first nodes. Also, a node in a Hierarchical Temporal Memory (HTM) network comprising a co-occurrence detector and a group learner coupled to the co-occurrence detector. The group learner provides an intra-node feedback signal to the co-occurrence detector including information on the grouping of the co-occurrences.Type: GrantFiled: March 21, 2008Date of Patent: July 19, 2011Assignee: Numenta, Inc.Inventors: Dileep George, Robert G. Jaros
-
Publication number: 20100049677Abstract: 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. At least one of the computing modules has a sequence learner module configured to associate sequences of input data received by the computing module to a set of causes previously learned in the hierarchy.Type: ApplicationFiled: October 9, 2009Publication date: February 25, 2010Applicant: NUMENTA, INC.Inventors: Robert G. Jaros, Dileep George, Jeffrey Hawkins, Frank Astier
-
Publication number: 20090313193Abstract: A temporal pooler for a Hierarchical Temporal Memory network is provided. The temporal pooler is capable of storing information about sequences of co-occurrences in a higher-order Markov chain by splitting a co-occurrence into a plurality of sub-occurrences. Each split sub-occurrence may be part of a distinct sequence of co-occurrences. The temporal pooler receives the probability of spatial co-occurrences in training patterns and tallies counts or frequency of transitions from one sub-occurrence to another sub-occurrence in a connectivity matrix. The connectivity matrix is then processed to generate temporal statistics data. The temporal statistics data is provided to an inference engine to perform inference or prediction on input patterns. By storing information related to a higher-order Markov model, the temporal statistics data more accurately reflects long temporal sequences of co-occurrences in the training patterns.Type: ApplicationFiled: June 12, 2009Publication date: December 17, 2009Applicant: NUMENTA, INC.Inventors: Jeffrey C. Hawkins, Dileep George, Charles Curry, Frank E. Astier, Anosh Raj, Robert G. Jaros
-
Patent number: 7620608Abstract: 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. At least one of the computing modules has a sequence learner module configured to associate sequences of input data received by the computing module to a set of causes previously learned in the hierarchy.Type: GrantFiled: January 11, 2007Date of Patent: November 17, 2009Assignee: Numenta, Inc.Inventors: Robert G. Jaros, Dileep George, Jeffrey Hawkins, Frank Astier
-
Publication number: 20090240639Abstract: A Hierarchical Temporal Memory (HTM) network has at least first nodes and a second node at a higher level than the first nodes. The second node provides an inter-node feedback signal to the first nodes for grouping patterns and sequences (or co-occurrences) in input data received at the first nodes at the first nodes. The second node collects forward signals from the first nodes; and thus, the second node has information about the grouping of the patterns and sequences (or co-occurrences) at the first nodes. The second node provides inter-node feedback signals to the first nodes based on which the first nodes may perform the grouping of the patterns and sequences (or co-occurrences) at the first nodes. Also, a node in a Hierarchical Temporal Memory (HTM) network comprising a co-occurrence detector and a group learner coupled to the co-occurrence detector. The group learner provides an intra-node feedback signal to the co-occurrence detector including information on the grouping of the co-occurrences.Type: ApplicationFiled: March 21, 2008Publication date: September 24, 2009Applicant: NUMENTA, INC.Inventors: Dileep George, Robert G. Jaros
-
Publication number: 20090006289Abstract: A node, a computer program storage medium, and a method for a hierarchical temporal memory (HTM) network where at least one of its nodes generates a top-down message and sends the top-down message to one or more children nodes in the HTM network. The first top-down message represents information about the state of a node and functions as feedback information from a current node to its child node. The node may also maintain history of the input patterns or co-occurrences so that temporal relationships between input patterns or co-occurrences may be taken into account in an inference stage. By providing the top-town message and maintaining history of previous input patterns, the HTM network may, among others, (i) perform more accurate inference based on temporal history, (ii) make predictions, (iii) discriminate between spatial co-occurrences with different temporal histories, (iv) detect “surprising” temporal patterns, (v) generate examples from a category, and (vi) fill in missing or occluded data.Type: ApplicationFiled: June 26, 2008Publication date: January 1, 2009Applicant: NUMENTA, INC.Inventors: Robert G. Jaros, Dileep George
-
Publication number: 20080208783Abstract: A spatio-temporal learning node is a type of HTM node which learns both spatial and temporal groups of sensed input patterns over time. Spatio-temporal learning nodes comprise spatial poolers which are used to determine spatial groups in a set of sensed input patterns. The spatio-temporal learning nodes further comprise temporal poolers which are used to determine groups of sensed input patterns that temporally co-occur. A spatio-temporal learning network is a hierarchical network including a plurality of spatio-temporal learning nodes.Type: ApplicationFiled: February 28, 2008Publication date: August 28, 2008Applicant: Numenta, Inc.Inventors: Robert G. Jaros, Jeffrey L. Edwards, Dileep George, Jeffrey C. Hawkins