Patents by Inventor D Scott Phoenix
D Scott Phoenix 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: 20220237431Abstract: A method for inferring patterns in multi-dimensional image data comprises providing a recursive network of sub-networks with a parent feature node and at least two child feature nodes; wherein each sub-network is associated with a distinct subset of the space; configuring nodes of the sub-networks with posterior distribution component; receiving image data feature input at the final child feature nodes; propagating node activation through the network layer hierarchy in a manner consistent with node connections of sub-networks of the network and the posterior prediction of child nodes; and outputting parent feature node selection to an inferred output.Type: ApplicationFiled: April 11, 2022Publication date: July 28, 2022Inventors: Dileep George, Kenneth Kansky, D. Scott Phoenix, Bhaskara Marthi, Christopher Laan, Wolfgang Lehrach
-
Patent number: 11315006Abstract: A method for inferring patterns in multi-dimensional image data comprises providing a recursive network of sub-networks with a parent feature node and at least two child feature nodes; wherein each sub-network is associated with a distinct subset of the space; configuring nodes of the sub-networks with posterior distribution component; receiving image data feature input at the final child feature nodes; propagating node activation through the network layer hierarchy in a manner consistent with node connections of sub-networks of the network and the posterior prediction of child nodes; and outputting parent feature node selection to an inferred output.Type: GrantFiled: March 17, 2017Date of Patent: April 26, 2022Assignee: Vicarious FPC, Inc.Inventors: Dileep George, Kenneth Kansky, D. Scott Phoenix, Bhaskara Marthi, Christopher Laan, Wolfgang Lehrach
-
Publication number: 20220083863Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.Type: ApplicationFiled: November 30, 2021Publication date: March 17, 2022Inventors: Austin Charles Stone, Huayan Wang, D. Scott Phoenix, Dileep George
-
Patent number: 11216727Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.Type: GrantFiled: December 14, 2018Date of Patent: January 4, 2022Assignee: Vicarious FPC, Inc.Inventors: Austin Charles Stone, Huayan Wang, D. Scott Phoenix, Dileep George
-
Patent number: 11188812Abstract: A system includes: a recursively architected network of sub-networks organized into a hierarchical layers; the sub-networks including at least a parent feature node, a pool node, a parent-specific child feature (PSCF) node, and a child feature node; the parent feature node of at least one sub-network configured with a selection function actionable on at least two pool nodes connected to the parent feature node of the at least one sub-network; the pool node of the at least one sub-network configured with a selection function actionable on at least two PSCF nodes connected to the pool node of the at least one sub-network; the PSCF node of the at least one sub-network configured to activate a connected child feature node; the child feature node connectable to at least a parent feature node of a sub-network at a lower hierarchical layer.Type: GrantFiled: May 18, 2016Date of Patent: November 30, 2021Assignee: Vicarious FPC, Inc.Inventors: Dileep George, Kenneth Kansky, D Scott Phoenix, Bhaskara Marthi, Christopher Laan, Wolfgang Lehrach
-
Publication number: 20190122112Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.Type: ApplicationFiled: December 14, 2018Publication date: April 25, 2019Inventors: Austin Charles Stone, Huayan Wang, D. Scott Phoenix, Dileep George
-
Patent number: 10185914Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.Type: GrantFiled: November 3, 2017Date of Patent: January 22, 2019Assignee: Vicarious FPC, Inc.Inventors: Austin Charles Stone, Huayan Wang, D. Scott Phoenix, Dileep George
-
Publication number: 20180121805Abstract: A system for teaching compositionality to convolutional neural networks includes an unmasked convolutional neural network comprising a first set of convolutional neural network layers; a first masked convolutional neural network comprising a second set of convolutional neural network layers; the unmasked convolutional neural network and the first masked convolutional network sharing convolutional neural network weights; the system training the unmasked and first masked convolutional neural networks simultaneously based on an objective function that seeks to reduce both discriminative loss and compositional loss.Type: ApplicationFiled: November 3, 2017Publication date: May 3, 2018Inventors: Austin Charles Stone, Huayan Wang, D. Scott Phoenix, Dileep George
-
Publication number: 20170193374Abstract: A method for inferring patterns in multi-dimensional image data comprises providing a recursive network of sub-networks with a parent feature node and at least two child feature nodes; wherein each sub-network is associated with a distinct subset of the space; configuring nodes of the sub-networks with posterior distribution component; receiving image data feature input at the final child feature nodes; propagating node activation through the network layer hierarchy in a manner consistent with node connections of sub-networks of the network and the posterior prediction of child nodes; and outputting parent feature node selection to an inferred output.Type: ApplicationFiled: March 17, 2017Publication date: July 6, 2017Inventors: Dileep George, Kenneth Kansky, D. Scott Phoenix, Bhaskara Marthi, Christopher Laan, Wolfgang Lehrach
-
Patent number: 9607263Abstract: A system includes: a recursively architected network of sub-networks organized into a hierarchical layers; the sub-networks including at least a parent feature node, a pool node, a parent-specific child feature (PSCF) node, and a child feature node; the parent feature node of at least one sub-network configured with a selection function actionable on at least two pool nodes connected to the parent feature node of the at least one sub-network; the pool node of the at least one sub-network configured with a selection function actionable on at least two PSCF nodes connected to the pool node of the at least one sub-network; the PSCF node of the at least one sub-network configured to activate a connected child feature node; the child feature node connectable to at least a parent feature node of a sub-network at a lower hierarchical layer.Type: GrantFiled: May 18, 2016Date of Patent: March 28, 2017Assignee: Vicarious FPC, Inc.Inventors: Dileep George, Kenneth Kansky, D Scott Phoenix, Bhaskara Marthi, Christopher Laan, Wolfgang Lehrach
-
Patent number: 9607262Abstract: A method for generating patterns with a network includes providing a recursive network of sub-networks with a parent feature node and at least two child feature nodes; and at a first sub-network of the recursive network, the first sub-network including the parent feature node and the at least two child feature nodes, selecting a first pool node and a second pool node consistent with a selection function of the parent feature node, selecting at least a first parent-specific child feature (PSCF) node that corresponds to a first child feature node of the sub-network, selecting at least a second parent-specific child feature (PSCF) node that corresponds to a second child feature node of the sub-network; and compiling the state of final child feature nodes, including the first and second child feature nodes, of the network into a generated output.Type: GrantFiled: May 18, 2016Date of Patent: March 28, 2017Assignee: Vicarious FPC, Inc.Inventors: Dileep George, Kenneth Kansky, D Scott Phoenix, Bhaskara Marthi, Christopher Laan, Wolfgang Lehrach
-
Publication number: 20160267375Abstract: A method for generating patterns with a network includes providing a recursive network of sub-networks with a parent feature node and at least two child feature nodes; and at a first sub-network of the recursive network, the first sub-network including the parent feature node and the at least two child feature nodes, selecting a first pool node and a second pool node consistent with a selection function of the parent feature node, selecting at least a first parent-specific child feature (PSCF) node that corresponds to a first child feature node of the sub-network, selecting at least a second parent-specific child feature (PSCF) node that corresponds to a second child feature node of the sub-network; and compiling the state of final child feature nodes, including the first and second child feature nodes, of the network into a generated output.Type: ApplicationFiled: May 18, 2016Publication date: September 15, 2016Inventors: Dileep George, Kenneth Kansky, D Scott Phoenix, Bhaskara Marthi, Christopher Laan, Wolfgang Lehrach
-
Publication number: 20160260009Abstract: A system includes: a recursively architected network of sub-networks organized into a hierarchical layers; the sub-networks including at least a parent feature node, a pool node, a parent-specific child feature (PSCF) node, and a child feature node; the parent feature node of at least one sub-network configured with a selection function actionable on at least two pool nodes connected to the parent feature node of the at least one sub-network; the pool node of the at least one sub-network configured with a selection function actionable on at least two PSCF nodes connected to the pool node of the at least one sub-network; the PSCF node of the at least one sub-network configured to activate a connected child feature node; the child feature node connectable to at least a parent feature node of a sub-network at a lower hierarchical layer.Type: ApplicationFiled: May 18, 2016Publication date: September 8, 2016Inventors: Dileep George, Kenneth Kansky, D Scott Phoenix, Bhaskara Marthi, Christopher Laan, Wolfgang Lehrach
-
Publication number: 20160260010Abstract: A system includes: a recursively architected network of sub-networks organized into a hierarchical layers; the sub-networks including at least a parent feature node, a pool node, a parent-specific child feature (PSCF) node, and a child feature node; the parent feature node of at least one sub-network configured with a selection function actionable on at least two pool nodes connected to the parent feature node of the at least one sub-network; the pool node of the at least one sub-network configured with a selection function actionable on at least two PSCF nodes connected to the pool node of the at least one sub-network; the PSCF node of the at least one sub-network configured to activate a connected child feature node; the child feature node connectable to at least a parent feature node of a sub-network at a lower hierarchical layer.Type: ApplicationFiled: May 18, 2016Publication date: September 8, 2016Inventors: Dileep George, Kenneth Kansky, D Scott Phoenix, Bhaskara Marthi, Christopher Laan, Wolfgang Lehrach