Patents by Inventor Anosh Raj
Anosh Raj 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).
-
Patent number: 11651277Abstract: A processing node in a temporal memory system includes a spatial pooler and a sequence processor. The spatial pooler generates a spatial pooler signal representing similarity between received spatial patterns in an input signal and stored co-occurrence patterns. The spatial pooler signal is represented by a combination of elements that are active or inactive. Each co-occurrence pattern is mapped to different subsets of elements of an input signal. The spatial pooler signal is fed to a sequence processor receiving and processed to learn, recognize and predict temporal sequences in the input signal. The sequence processor includes one or more columns, each column including one or more cells. A subset of columns may be selected by the spatial pooler signal, causing one or more cells in these columns to activate.Type: GrantFiled: November 26, 2019Date of Patent: May 16, 2023Assignee: Numenta, Inc.Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Patent number: 11270202Abstract: A processing node in a temporal memory system includes a spatial pooler and a sequence processor. The spatial pooler generates a spatial pooler signal representing similarity between received spatial patterns in an input signal and stored co-occurrence patterns. The spatial pooler signal is represented by a combination of elements that are active or inactive. Each co-occurrence pattern is mapped to different subsets of elements of an input signal. The spatial pooler signal is fed to a sequence processor receiving and processed to learn, recognize and predict temporal sequences in the input signal. The sequence processor includes one or more columns, each column including one or more cells. A subset of columns may be selected by the spatial pooler signal, causing one or more cells in these columns to activate.Type: GrantFiled: March 4, 2019Date of Patent: March 8, 2022Assignee: Numenta, Inc.Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Publication number: 20200097857Abstract: A processing node in a temporal memory system includes a spatial pooler and a sequence processor. The spatial pooler generates a spatial pooler signal representing similarity between received spatial patterns in an input signal and stored co-occurrence patterns. The spatial pooler signal is represented by a combination of elements that are active or inactive. Each co-occurrence pattern is mapped to different subsets of elements of an input signal. The spatial pooler signal is fed to a sequence processor receiving and processed to learn, recognize and predict temporal sequences in the input signal. The sequence processor includes one or more columns, each column including one or more cells. A subset of columns may be selected by the spatial pooler signal, causing one or more cells in these columns to activate.Type: ApplicationFiled: November 26, 2019Publication date: March 26, 2020Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Publication number: 20190236481Abstract: A processing node in a temporal memory system includes a spatial pooler and a sequence processor. The spatial pooler generates a spatial pooler signal representing similarity between received spatial patterns in an input signal and stored co-occurrence patterns. The spatial pooler signal is represented by a combination of elements that are active or inactive. Each co-occurrence pattern is mapped to different subsets of elements of an input signal. The spatial pooler signal is fed to a sequence processor receiving and processed to learn, recognize and predict temporal sequences in the input signal. The sequence processor includes one or more columns, each column including one or more cells. A subset of columns may be selected by the spatial pooler signal, causing one or more cells in these columns to activate.Type: ApplicationFiled: March 4, 2019Publication date: August 1, 2019Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Patent number: 10275720Abstract: A processing node in a temporal memory system includes a spatial pooler and a sequence processor. The spatial pooler generates a spatial pooler signal representing similarity between received spatial patterns in an input signal and stored co-occurrence patterns. The spatial pooler signal is represented by a combination of elements that are active or inactive. Each co-occurrence pattern is mapped to different subsets of elements of an input signal. The spatial pooler signal is fed to a sequence processor receiving and processed to learn, recognize and predict temporal sequences in the input signal. The sequence processor includes one or more columns, each column including one or more cells. A subset of columns may be selected by the spatial pooler signal, causing one or more cells in these columns to activate.Type: GrantFiled: October 9, 2015Date of Patent: April 30, 2019Assignee: NUMENTA, INC.Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Patent number: 9552551Abstract: A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.Type: GrantFiled: June 27, 2014Date of Patent: January 24, 2017Assignee: Numenta, Inc.Inventors: Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Patent number: 9471663Abstract: Systems and methods for classifying media items in a media system are provided. In particular, media items can be uploaded to a serve. Data describing the media items can be monitored. Alterations of data describing the media items or inconsistencies of the data describing can be detected. A corrective action can be determined based on the alterations and or the inconsistencies. The corrective action can manage media items in multiple classification systems.Type: GrantFiled: January 22, 2014Date of Patent: October 18, 2016Assignee: Google Inc.Inventors: Johan Georg Granström, Anosh Raj
-
Publication number: 20160086098Abstract: A processing node in a temporal memory system includes a spatial pooler and a sequence processor. The spatial pooler generates a spatial pooler signal representing similarity between received spatial patterns in an input signal and stored co-occurrence patterns. The spatial pooler signal is represented by a combination of elements that are active or inactive. Each co-occurrence pattern is mapped to different subsets of elements of an input signal. The spatial pooler signal is fed to a sequence processor receiving and processed to learn, recognize and predict temporal sequences in the input signal. The sequence processor includes one or more columns, each column including one or more cells. A subset of columns may be selected by the spatial pooler signal, causing one or more cells in these columns to activate.Type: ApplicationFiled: October 9, 2015Publication date: March 24, 2016Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Patent number: 9189745Abstract: A processing node in a temporal memory system includes a spatial pooler and a sequence processor. The spatial pooler generates a spatial pooler signal representing similarity between received spatial patterns in an input signal and stored co-occurrence patterns. The spatial pooler signal is represented by a combination of elements that are active or inactive. Each co-occurrence pattern is mapped to different subsets of elements of an input signal. The spatial pooler signal is fed to a sequence processor receiving and processed to learn, recognize and predict temporal sequences in the input signal. The sequence processor includes one or more columns, each column including one or more cells. A subset of columns may be selected by the spatial pooler signal, causing one or more cells in these columns to activate.Type: GrantFiled: March 11, 2011Date of Patent: November 17, 2015Assignee: Numenta, Inc.Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Patent number: 9002175Abstract: Methods, systems, and computer program products for automatic creation of video trailers are provided. A computer-implemented method may include computing blended audience retention for video segments based on audience retention rates for each of the video segments across corresponding points in time, analyzing the blended audience retention for the video segments across corresponding points in time, identifying one or more audience engagement peaks for the video segments based on the analyzing, selecting one or more video clips from the video segments based on the identified audience engagement peaks, and generating a video trailer using the selected video clips into a new video.Type: GrantFiled: March 13, 2013Date of Patent: April 7, 2015Assignee: Google Inc.Inventor: Anosh Raj
-
Publication number: 20140310227Abstract: A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.Type: ApplicationFiled: June 27, 2014Publication date: October 16, 2014Inventors: Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Publication number: 20140310226Abstract: A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.Type: ApplicationFiled: June 27, 2014Publication date: October 16, 2014Inventors: Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Patent number: 8825565Abstract: A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.Type: GrantFiled: August 25, 2011Date of Patent: September 2, 2014Assignee: Numenta, Inc.Inventors: Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Patent number: 8645291Abstract: A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.Type: GrantFiled: August 25, 2011Date of Patent: February 4, 2014Assignee: Numenta, Inc.Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj
-
Patent number: 8504570Abstract: A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.Type: GrantFiled: August 25, 2011Date of Patent: August 6, 2013Assignee: Numenta, Inc.Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
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: 20130054496Abstract: A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.Type: ApplicationFiled: August 25, 2011Publication date: February 28, 2013Applicant: NUMENTA, INC.Inventors: Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Publication number: 20130054552Abstract: A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.Type: ApplicationFiled: August 25, 2011Publication date: February 28, 2013Applicant: NUMENTA, INC.Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj, Subutai Ahmad
-
Publication number: 20130054495Abstract: A spatial and temporal memory system (STMS) processes input data to detect whether spatial patterns and/or temporal sequences of spatial patterns exist within the data, and to make predictions about future data. The data processed by the STMS may be retrieved from, for example, one or more database fields and is encoded into a distributed representation format using a coding scheme. The performance of the STMS in predicting future data is evaluated for the coding scheme used to process the data as performance data. The selection and prioritization of STMS experiments to perform may be based on the performance data for an experiment. The best fields, encodings, and time aggregations for generating predictions can be determined by an automated search and evaluation of multiple STMS systems.Type: ApplicationFiled: August 25, 2011Publication date: February 28, 2013Applicant: NUMENTA, INC.Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj
-
Publication number: 20110225108Abstract: A processing node in a temporal memory system includes a spatial pooler and a sequence processor. The spatial pooler generates a spatial pooler signal representing similarity between received spatial patterns in an input signal and stored co-occurrence patterns. The spatial pooler signal is represented by a combination of elements that are active or inactive. Each co-occurrence pattern is mapped to different subsets of elements of an input signal. The spatial pooler signal is fed to a sequence processor receiving and processed to learn, recognize and predict temporal sequences in the input signal. The sequence processor includes one or more columns, each column including one or more cells. A subset of columns may be selected by the spatial pooler signal, causing one or more cells in these columns to activate.Type: ApplicationFiled: March 11, 2011Publication date: September 15, 2011Applicant: NUMENTA, INC.Inventors: Jeffrey C. Hawkins, Ronald Marianetti, II, Anosh Raj, Subutai Ahmad