Patents by Inventor Henry Markram
Henry Markram 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: 20240111994Abstract: Application of the output from a recurrent artificial neural network to a variety of different applications. A method can include identifying topological patterns of activity in a recurrent artificial neural network, outputting a collection of digits, and inputting a first digit of the collection to a first application that is designed to fulfil a first purpose and to a second application that is designed to fulfil a second purpose, wherein the first purpose differs from the second purpose. The topological patterns are responsive to an input of data into the recurrent artificial neural network and each topological pattern abstracts a characteristic of the input data. Each digit represents whether one of the topological patterns of activity has been identified in the artificial neural network.Type: ApplicationFiled: October 16, 2023Publication date: April 4, 2024Inventors: Henry Markram, Felix Schürmann, Fabien Jonathan Delalondre, Daniel Milan Lütgehetmann, John Rahmon, Constantin Cosmin Atanasoaei, Michele De Gruttola
-
Patent number: 11900237Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for organizing trained and untrained neural networks. In one aspect, a neural network device includes a collection of node assemblies interconnected by between-assembly links, each node assembly itself comprising a network of nodes interconnected by a plurality of within-assembly links, wherein each of the between-assembly links and the within-assembly links have an associated weight, each weight embodying a strength of connection between the nodes joined by the associated link, the nodes within each assembly being more likely to be connected to other nodes within that assembly than to be connected to nodes within others of the node assemblies.Type: GrantFiled: September 20, 2021Date of Patent: February 13, 2024Assignee: ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)Inventors: Henry Markram, Rodrigo de Campos Perin, Thomas K. Berger
-
Publication number: 20240046077Abstract: Abstracting data that originates from different sensors and transducers using artificial neural networks. A method can include identifying topological patterns of activity in a recurrent artificial neural network and outputting a collection of digits. The topological patterns are responsive to an input, into the recurrent artificial neural network, of first data originating from a first sensor and second data originating from a second sensor. Each topological pattern abstracts a characteristic shared by the first data and the second data. The first and second sensors sense different data. Each digit represents whether one of the topological patterns of activity has been identified in the artificial neural network.Type: ApplicationFiled: October 20, 2023Publication date: February 8, 2024Inventors: Henry Markram, Felix Schürmann, Fabien Jonathan Delalondre, Daniel Milan Lütgehetmann, John Rahmon
-
Patent number: 11893471Abstract: In one implementation, a method is implemented by a neural network device and includes inputting a representation of topological structures in patterns of activity in a source neural network, wherein the activity is responsive to an input into the source neural network, processing the representation, and outputting a result of the processing of the representation. The processing is consistent with a training of the neural network to process different such representations of topological structures in patterns of activity in the source neural network.Type: GrantFiled: June 11, 2018Date of Patent: February 6, 2024Assignee: INAIT SAInventors: Henry Markram, Ran Levi, Kathryn Pamela Hess Bellwald, Felix Schuermann
-
Publication number: 20230394280Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for organizing trained and untrained neural networks. In one aspect, a neural network device includes a collection of node assemblies interconnected by between-assembly links, each node assembly itself comprising a network of nodes interconnected by a plurality of within-assembly links, wherein each of the between-assembly links and the within-assembly links have an associated weight, each weight embodying a strength of connection between the nodes joined by the associated link, the nodes within each assembly being more likely to be connected to other nodes within that assembly than to be connected to nodes within others of the node assemblies.Type: ApplicationFiled: September 20, 2021Publication date: December 7, 2023Inventors: Henry Markram, Rodrigo de Campos Perin, Thomas K. Berger
-
Publication number: 20230370244Abstract: Methods, systems, and devices for homomorphic encryption. In one implementation, the methods include inputting first data into a recurrent artificial neural network, identifying patterns of activity in the recurrent artificial neural network that are responsive to the input of the secure data, storing second data representing whether the identified patterns of activity comports with topological patterns, and statistically analyzing the second data to draw conclusions about the first data.Type: ApplicationFiled: April 5, 2023Publication date: November 16, 2023Inventors: Henry Markram, Felix Schuermann, Kathryn Hess Bellwald, Fabien Delalondre
-
Patent number: 11816553Abstract: Application of the output from a recurrent artificial neural network to a variety of different applications. A method can include identifying topological patterns of activity in a recurrent artificial neural network, outputting a collection of digits, and inputting a first digit of the collection to a first application that is designed to fulfil a first purpose and to a second application that is designed to fulfil a second purpose, wherein the first purpose differs from the second purpose. The topological patterns are responsive to an input of data into the recurrent artificial neural network and each topological pattern abstracts a characteristic of the input data. Each digit represents whether one of the topological patterns of activity has been identified in the artificial neural network.Type: GrantFiled: December 11, 2019Date of Patent: November 14, 2023Assignee: INAIT SAInventors: Henry Markram, Felix Schürmann, Fabien Jonathan Delalondre, Daniel Milan Lütgehetmann, John Rahmon, Constantin Cosmin Atanasoaei, Michele De Gruttola
-
Patent number: 11817220Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reconstructing and simulating neocortical microcircuitry. In one aspect, a method includes providing a model of neural tissue, the model including different types of neural cells and dynamic synaptic interconnections between the neural cells, changing a parameter in the model; and identifying a change in a computational state of the model of the neural tissue responsive to the change in the parameter. The change in the parameter can, e.g., change behavior of neural cells of at least one type, change interconnectivity between neural cells, or target a location within a volume in the model that interacts with multiple types of neural cells.Type: GrantFiled: October 10, 2017Date of Patent: November 14, 2023Assignee: ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)Inventors: Henry Markram, Eilif Benjamin Muller, Sean Lewis Hill, Felix Schuermann
-
Publication number: 20230351196Abstract: Distance metrics and clustering in recurrent neural networks. For example, a method includes determining whether topological patterns of activity in a collection of topological patterns occur in a recurrent artificial neural network in response to input of first data into the recurrent artificial neural network, and determining a distance between the first data and either second data or a reference based on the topological patterns of activity that are determined to occur in response to the input of the first data.Type: ApplicationFiled: February 13, 2023Publication date: November 2, 2023Inventors: Henry MARKRAM, Felix Schurmann, Fabien Jonathan Delalondre, Ran Levi, Kathryn Hess Bellwald, John Rahmon
-
Patent number: 11797827Abstract: Abstracting data that originates from different sensors and transducers using artificial neural networks. A method can include identifying topological patterns of activity in a recurrent artificial neural network and outputting a collection of digits. The topological patterns are responsive to an input, into the recurrent artificial neural network, of first data originating from a first sensor and second data originating from a second sensor. Each topological pattern abstracts a characteristic shared by the first data and the second data. The first and second sensors sense different data. Each digit represents whether one of the topological patterns of activity has been identified in the artificial neural network.Type: GrantFiled: December 11, 2019Date of Patent: October 24, 2023Assignee: INAIT SAInventors: Henry Markram, Felix Schürmann, Fabien Jonathan Delalondre, Daniel Milan Lütgehetmann, John Rahmon
-
Publication number: 20230316077Abstract: A method includes defining a plurality of different windows of time in a recurrent artificial neural network, wherein each of the different windows has different durations, has different start times, or has both different durations and different start times, identifying occurrences of topological patterns of activity in the recurrent artificial neural network in the different windows of time, comparing the occurrences of the topological patterns of activity in the different windows, and classifying, based on a result of the comparison, a first decision that is represented by a first topological pattern of activity that occurs in a first of the windows as less robust than a second decision that is represented by a second topological pattern of activity that occurs in a second of the windows.Type: ApplicationFiled: April 5, 2023Publication date: October 5, 2023Inventors: Henry Markram, Felix Schuermann, John Rahmon, Daniel Milan Lütgehetmann, Constantin Cosmin Atanasoaei
-
Publication number: 20230297808Abstract: In one aspect, a method includes generating a functional subgraph of a network from a structural graph of the network. The structural graph comprises a set of vertices and structural connections between the vertices. Generating the functional subgraph includes identifying a directed functional edge of the functional subgraph based on presence of structural connection and directional communication of information across the same structural connection.Type: ApplicationFiled: March 23, 2023Publication date: September 21, 2023Inventors: Michael Wolfgang Reimann, Max Christian Nolte, Henry Markram, Kathryn Hess Bellwald, Ran Levi
-
Publication number: 20230171086Abstract: Methods, systems, and devices for encrypting and decrypting data. In one implementation, an encryption method includes inputting plaintext into a recurrent artificial neural network, identifying topological structures in patterns of activity in the recurrent artificial neural network, wherein the patterns of activity are responsive to the input of the plaintext, representing the identified topological structures in a binary sequence of length L and implementing a permutation of the set of all binary codewords of length L. The implemented permutation is a function from the set of binary codewords of length L to itself that is injective and surjective.Type: ApplicationFiled: January 30, 2023Publication date: June 1, 2023Inventors: Kathryn Hess Bellwald, Henry Markram
-
Patent number: 11663478Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for characterizing activity in a recurrent artificial neural network. In one aspect, a method for identifying decision moments in a recurrent artificial neural network includes determining a complexity of patterns of activity in the recurrent artificial neural network, wherein the activity is responsive to input into the recurrent artificial neural network, determining a timing of activity having a complexity that is distinguishable from other activity that is responsive to the input, and identifying the decision moment based on the timing of the activity that has the distinguishable complexity.Type: GrantFiled: June 11, 2018Date of Patent: May 30, 2023Assignee: INAIT SAInventors: Henry Markram, Ran Levi, Kathryn Pamela Hess Bellwald
-
Patent number: 11651210Abstract: A method includes defining a plurality of different windows of time in a recurrent artificial neural network, wherein each of the different windows has different durations, has different start times, or has both different durations and different start times, identifying occurrences of topological patterns of activity in the recurrent artificial neural network in the different windows of time, comparing the occurrences of the topological patterns of activity in the different windows, and classifying, based on a result of the comparison, a first decision that is represented by a first topological pattern of activity that occurs in a first of the windows as less robust than a second decision that is represented by a second topological pattern of activity that occurs in a second of the windows.Type: GrantFiled: December 11, 2019Date of Patent: May 16, 2023Assignee: INAIT SAInventors: Henry Markram, Felix Schürmann, John Rahmon, Daniel Milan Lütgehetmann, Constantin Cosmin Atanasoaei
-
Patent number: 11652603Abstract: Methods, systems, and devices for homomorphic encryption. In one implementation, the methods include inputting first data into a recurrent artificial neural network, identifying patterns of activity in the recurrent artificial neural network that are responsive to the input of the secure data, storing second data representing whether the identified patterns of activity comports with topological patterns, and statistically analyzing the second data to draw conclusions about the first data.Type: GrantFiled: March 18, 2019Date of Patent: May 16, 2023Assignee: INAIT SAInventors: Henry Markram, Felix Schuermann, Kathryn Hess, Fabien Delalondre
-
Patent number: 11615285Abstract: In one aspect, a method includes generating a functional subgraph of a network from a structural graph of the network. The structural graph comprises a set of vertices and structural connections between the vertices. Generating the functional subgraph includes identifying a directed functional edge of the functional subgraph based on presence of structural connection and directional communication of information across the same structural connection.Type: GrantFiled: January 8, 2018Date of Patent: March 28, 2023Assignee: Ecole Polytechnique Federale De Lausanne (EPFL)Inventors: Michael Wolfgang Reimann, Max Christian Nolte, Henry Markram, Kathryn Pamela Hess Bellwald, Ran Levi
-
Patent number: 11580401Abstract: Distance metrics and clustering in recurrent neural networks. For example, a method includes determining whether topological patterns of activity in a collection of topological patterns occur in a recurrent artificial neural network in response to input of first data into the recurrent artificial neural network, and determining a distance between the first data and either second data or a reference based on the topological patterns of activity that are determined to occur in response to the input of the first data.Type: GrantFiled: December 11, 2019Date of Patent: February 14, 2023Inventors: Henry Markram, Felix Schürmann, Fabien Jonathan Delalondre, Ran Levi, Kathryn Pamela Hess Bellwald, John Rahmon
-
Patent number: 11569978Abstract: Methods, systems, and devices for encrypting and decrypting data. In one implementation, an encryption method includes inputting plaintext into a recurrent artificial neural network, identifying topological structures in patterns of activity in the recurrent artificial neural network, wherein the patterns of activity are responsive to the input of the plaintext, representing the identified topological structures in a binary sequence of length L and implementing a permutation of the set of all binary codewords of length L. The implemented permutation is a function from the set of binary codewords of length L to itself that is injective and surjective.Type: GrantFiled: March 18, 2019Date of Patent: January 31, 2023Assignee: INAIT SAInventors: Kathryn Hess, Henry Markram
-
Publication number: 20230024925Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting a set of elements that form a cognitive process in a recurrent neural network. The method comprises identifying activity in the recurrent neural network that comports with relatively simple topological patterns, using the identified relatively simple topological patterns as a constraint to identify relatively more complex topological patterns of activity in the recurrent neural network, using the identified relatively more complex topological patterns as a constraint to identify relatively still more complex topological patterns of activity in the recurrent neural network, and outputting identifications of the topological patterns of activity that have occurred in the recurrent neural network.Type: ApplicationFiled: December 11, 2020Publication date: January 26, 2023Inventor: Henry Markram