Patents by Inventor Thomas K. Berger
Thomas K. Berger 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: 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: 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: 20220121907Abstract: 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: April 21, 2022Inventors: Henry Markram, Rodrigo de Perin, Thomas K. Berger
-
Patent number: 11126911Abstract: 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: August 1, 2019Date of Patent: September 21, 2021Assignee: Ecole Polytechnique Federale De Lausanne (EPFL)Inventors: Henry Markram, Rodrigo de Campos Perin, Thomas K. Berger
-
Publication number: 20190354841Abstract: 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: August 1, 2019Publication date: November 21, 2019Inventors: Henry Markram, Rodrigo de Campos Perin, Thomas K. Berger
-
Patent number: 10387767Abstract: 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: August 3, 2012Date of Patent: August 20, 2019Assignee: Ecole Polytechnique Federale De Lausanne (EPFL)Inventors: Henry Markram, Rodrigo de Campos Perin, Thomas K. Berger
-
Patent number: 10373048Abstract: 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: August 27, 2015Date of Patent: August 6, 2019Assignee: Ecole Polytechnique Federale De Lausanne (EPFL)Inventors: Henry Markram, Rodrigo de Campos Perin, Thomas K. Berger
-
Publication number: 20150363689Abstract: 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: August 27, 2015Publication date: December 17, 2015Inventors: Henry Markram, Rodrigo de Campos Perin, Thomas K. Berger
-
Publication number: 20120323833Abstract: 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: August 3, 2012Publication date: December 20, 2012Applicant: ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)Inventors: Henry Markram, Rodrigo de Campos Perin, Thomas K. Berger