Patents by Inventor James Bradley Aimone
James Bradley Aimone 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: 11880448Abstract: A computer-implemented method of user authentication is provided. The method comprises combining, by a computer system, a user recurrent neural network with a system recurrent neural network to form a unique combined recurrent neural network. The user recurrent neural network is configured to generate a unique user key, and the system recurrent neural network is configured to generate a system key. The computer system inputs a predetermined input into the combined recurrent neural network, and the combined recurrent neural network generates a unique combined key from the input, wherein the combined key differs from both the user key and system key. The computer system then associates the combined key with a unique access authorization to authenticate a user.Type: GrantFiled: March 9, 2021Date of Patent: January 23, 2024Assignee: National Technology & Engineering Solutions of Sandia, LLCInventors: James Bradley Aimone, Jason Hamlet, Tu-Thach Quach
-
Patent number: 11755891Abstract: A method for increasing a speed and efficiency of a computer when performing machine learning using spiking neural networks. The method includes computer-implemented operations; that is, operations that are solely executed on a computer. The method includes receiving, in a spiking neural network, a plurality of input values upon which a machine learning algorithm is based. The method also includes correlating, for each input value, a corresponding response speed of a corresponding neuron to a corresponding equivalence relationship between the input value to a corresponding latency of the corresponding neuron. Neurons that trigger faster than other neurons represent close relationships between input values and neuron latencies. Latencies of the neurons represent data points used in performing the machine learning. A plurality of equivalence relationships are formed as a result of correlating. The method includes performing the machine learning using the plurality of equivalence relationships.Type: GrantFiled: June 20, 2018Date of Patent: September 12, 2023Assignee: National Technology & Engineering Solutions of Sandia, LLCInventors: Craig Michael Vineyard, William Mark Severa, James Bradley Aimone, Stephen Joseph Verzi
-
Publication number: 20220406408Abstract: Anomaly detection for streaming data is provided. A spiking neural network receives inputs of streaming data, wherein each input is contained within a number of neighborhoods and converts the inputs into phase-coded spikes. A median value of each input is calculated for each size neighborhood containing the input, and an absolute difference of each input from its median value is calculated for each size neighborhood. From the absolute differences, a median absolute difference (MAD) value of each input is calculated for each size neighborhood. It is determined whether the MAD value for any size neighborhood exceeds a respective threshold. If the MAD value exceeds its threshold, an anomaly indication is output for the input. If none of the MAD values for the neighborhoods exceeds its threshold, a normal indication is output for the input.Type: ApplicationFiled: August 18, 2022Publication date: December 22, 2022Inventors: Stephen Joseph Verzi, Craig Michael Vineyard, James Bradley Aimone
-
Publication number: 20220292364Abstract: A method for simulating a random walk using spiking neuromorphic hardware is provided. The method comprises receiving, by a buffer count neuron, spiking inputs from upstream mesh nodes, wherein the inputs include information packets comprising information associated with a simulation of a random walk process. A buffer generator neuron generates spikes until the buffer count reaches a first predefined threshold, after which it sends buffer spiking outputs to a spike count neuron. The spike count neuron counts the buffer spiking outputs, and a spike generator neuron generates spikes until the spike count neuron reaches a second specified threshold. The spike generator neuron then sends counter spiking outputs to a probability neuron, which selects downstream mesh nodes to receive the counter spiking outputs, wherein the spiking outputs include updated information packets. The probability neuron then sends the spiking outputs to the selected downstream nodes.Type: ApplicationFiled: March 12, 2021Publication date: September 15, 2022Inventors: James Bradley Aimone, William Mark Severa, John Darby Smith
-
Patent number: 11436475Abstract: Detecting anomalies with a spiking neural network is provided. An input layer receives a number of inputs and converts them into phase-coded spikes, wherein each input is contained within a number of progressively larger neighborhoods of surrounding inputs. From the phase-coded spikes, a median value of each input is computed for each size neighborhood. An absolute difference of each input from its median value is computed for each size neighborhood. A median absolute difference (MAD) of each input is computed for each size neighborhood. For each input, an adaptive median filter (AMF) determines if a MAD for any size neighborhood exceeds a respective threshold. If one or more neighborhoods exceeds its threshold, the AMF outputs the median value of the input for the smallest neighborhood. If none of the neighborhoods exceeds the threshold, the AMF outputs the original value of the input.Type: GrantFiled: June 10, 2019Date of Patent: September 6, 2022Assignee: National Technology & Engineering Solutions of Sandia, LLCInventors: Stephen Joseph Verzi, Craig Michael Vineyard, James Bradley Aimone
-
Patent number: 11409922Abstract: A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space, wherein the virtual space comprises a plurality of vertices and wherein the different locations are ones of the plurality of vertices. A corresponding set of neurons in a spiking neural network is assigned to a corresponding vertex such that there is a correspondence between sets of neurons and the plurality of vertices, wherein a spiking neural network comprising a plurality of sets of spiking neurons is established. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network, wherein executing includes tracking how many virtual random walkers are at each vertex at a given time increment.Type: GrantFiled: June 27, 2018Date of Patent: August 9, 2022Assignee: National Technology & Engineering Solutions of Sandia, LLCInventors: James Bradley Aimone, William Mark Severa, Richard B. Lehoucq, Ojas D. Parekh
-
Patent number: 11281964Abstract: A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space. The method also includes either assigning a corresponding set of ringed neurons in a spiking neural network to a corresponding virtual random walker, or assigning a corresponding set of ringed neurons to a point in the virtual space. Movement of a given virtual random walker is tracked by decoding differences between states of individual neurons in a corresponding given set of ringed neurons. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network.Type: GrantFiled: June 27, 2018Date of Patent: March 22, 2022Assignee: National Technology & Engineering Solutions of Sandia, LLCInventors: James Bradley Aimone, William Mark Severa, Richard B. Lehoucq, Ojas D. Parekh
-
Publication number: 20220027712Abstract: A programmable logic unit is provided. The logic unit comprises a number of crossbar arrays. A control circuit connected to the crossbar arrays is configured to provide inputs to a specified subset of crossbar arrays according to a program. A layer of spiking neurons is connected to the crossbar arrays, wherein respective outputs from the crossbar arrays are summed together and input into the spiking neurons. A temporal buffer circuit is configured to hold spiking activation signals from the spiking neurons for a delay time specified by the program before routing the spiking activation signals back to the crossbar arrays as input through the control circuit.Type: ApplicationFiled: July 27, 2020Publication date: January 27, 2022Inventor: James Bradley Aimone
-
Patent number: 11023579Abstract: A method and apparatus for monitoring a volatile memory in a computer system. Samples of compressed data from locations in the volatile memory in the computer system are read. Data in the volatile memory is reconstructed using the samples of compressed data. The data is an image of the volatile memory. The image enables determining whether an undesired process is present in the volatile memory.Type: GrantFiled: December 1, 2016Date of Patent: June 1, 2021Assignee: National Technology & Engineering Solutions of Sandia, LLCInventors: Jason W. Wheeler, Tu-Thach Quach, Conrad D. James, James Bradley Aimone, Arun F. Rodrigues
-
Patent number: 10970630Abstract: Various technologies pertaining to allocating computing resources of a neuromorphic computing system are described herein. Subgraphs of a neural algorithm graph to be executed by the neuromorphic computing system are identified. The subgraphs are each executed by a group of neuron circuits serially. Output data generated by execution of the subgraphs are provided to the same or a second group of neuron circuits at a same time or with associated timing data indicative of a time at which the output data was generated. The same or second group of neuron circuits performs one or more processing operations based upon the output data.Type: GrantFiled: June 15, 2017Date of Patent: April 6, 2021Assignees: National Technology & Engineering Solutions of Sandia, LLC, Lewis Rhodes Labs, Inc.Inventors: James Bradley Aimone, John H. Naegle, Jonathon W. Donaldson, David Follett, Pamela Follett
-
Patent number: 10891540Abstract: A method and computer system for managing a neural network. Data is sent into an input layer in a portion of layers of nodes in the neural network. The data moves on an encode path through the portion such that an output layer in the portion outputs encoded data. The encoded data is sent into the output layer on a decode path through the portion back to the input layer to obtain a reconstruction of the data by the input layer. A determination is made as to whether an undesired amount of error has occurred in the output layer based on the data sent into the input layer and the reconstruction of the data. A number of new nodes is added to the output layer when a determination is present that the undesired amount of the error occurred, enabling reducing the error using the number of the new nodes.Type: GrantFiled: December 18, 2015Date of Patent: January 12, 2021Assignee: National Technology & Engineering Solutions of Sandia, LLCInventors: Timothy J. Draelos, James Bradley Aimone
-
Publication number: 20200387773Abstract: Detecting anomalies with a spiking neural network is provided. An input layer receives a number of inputs and converts them into phase-coded spikes, wherein each input is contained within a number of progressively larger neighborhoods of surrounding inputs. From the phase-coded spikes, a median value of each input is computed for each size neighborhood. An absolute difference of each input from its median value is computed for each size neighborhood. A median absolute difference (MAD) of each input is computed for each size neighborhood. For each input, an adaptive median filter (AMF) determines if a MAD for any size neighborhood exceeds a respective threshold. If one or more neighborhoods exceeds its threshold, the AMF outputs the median value of the input for the smallest neighborhood. If none of the neighborhoods exceeds the threshold, the AMF outputs the original value of the input.Type: ApplicationFiled: June 10, 2019Publication date: December 10, 2020Inventors: Stephen Joseph Verzi, Craig Michael Vineyard, James Bradley Aimone
-
Patent number: 10649663Abstract: A method and system for accessing a memory for a data processing system. The method comprises sending a read request for a plurality of locations in the memory to read the plurality of locations in parallel based on an upper bound for reading the memory. The upper bound for a number of locations is based on a group of constraints for the memory. The method receives a summed value of a plurality of memory values in the plurality of locations in the memory.Type: GrantFiled: July 31, 2017Date of Patent: May 12, 2020Assignee: National Technology & Engineering Solutions of Sandia, LLCInventors: Conrad D. James, Tu-Thach Quach, Sapan Agarwal, James Bradley Aimone
-
Publication number: 20200110997Abstract: An artificial neural network with a context pathway and a method of identifying a classification of information using an artificial neural network with a context pathway. An artificial neural network comprises up-stream layers and down-stream layers. An output of the up-stream layers is provided as input to the down-stream layers. A first input to the artificial neural network to the up-stream layers is configured to receive input data. A second input to the artificial neural network to the down-stream layers is configured to receive context data. The context data identifies a characteristic of information in the input data. The artificial neural network is configured to identify a classification of the information in the input data at an output of the down-stream layers using the context data.Type: ApplicationFiled: October 5, 2018Publication date: April 9, 2020Inventors: William Mark Severa, James Bradley Aimone
-
Publication number: 20200005120Abstract: A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space. The method also includes either assigning a corresponding set of ringed neurons in a spiking neural network to a corresponding virtual random walker, or assigning a corresponding set of ringed neurons to a point in the virtual space. Movement of a given virtual random walker is tracked by decoding differences between states of individual neurons in a corresponding given set of ringed neurons. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network.Type: ApplicationFiled: June 27, 2018Publication date: January 2, 2020Inventors: James Bradley Aimone, William Mark Severa, Richard B. Lehoucq, Ojas D. Parekh
-
Publication number: 20200004902Abstract: A method for increasing a speed or energy efficiency at which a computer is capable of modeling a plurality of random walkers. The method includes defining a virtual space in which a plurality of virtual random walkers will move among different locations in the virtual space, wherein the virtual space comprises a plurality of vertices and wherein the different locations are ones of the plurality of vertices. A corresponding set of neurons in a spiking neural network is assigned to a corresponding vertex such that there is a correspondence between sets of neurons and the plurality of vertices, wherein a spiking neural network comprising a plurality of sets of spiking neurons is established. A virtual random walk of the plurality of virtual random walkers is executed using the spiking neural network, wherein executing includes tracking how many virtual random walkers are at each vertex at a given time increment.Type: ApplicationFiled: June 27, 2018Publication date: January 2, 2020Inventors: James Bradley Aimone, William Mark Severa, Richard B. Lehoucq, Ojas D. Parekh
-
Publication number: 20190392301Abstract: A method for increasing a speed and efficiency of a computer when performing machine learning using spiking neural networks. The method includes computer-implemented operations; that is, operations that are solely executed on a computer. The method includes receiving, in a spiking neural network, a plurality of input values upon which a machine learning algorithm is based. The method also includes correlating, for each input value, a corresponding response speed of a corresponding neuron to a corresponding equivalence relationship between the input value to a corresponding latency of the corresponding neuron. Neurons that trigger faster than other neurons represent close relationships between input values and neuron latencies. Latencies of the neurons represent data points used in performing the machine learning. A plurality of equivalence relationships are formed as a result of correlating. The method includes performing the machine learning using the plurality of equivalence relationships.Type: ApplicationFiled: June 20, 2018Publication date: December 26, 2019Inventors: Craig Michael Vineyard, William Mark Severa, James Bradley Aimone, Stephen Joseph Verzi
-
Patent number: 10445065Abstract: A method of increasing an efficiency at which a plurality of threshold gates arranged as neuromorphic hardware is able to perform a linear algebraic calculation having a dominant size of N. The computer-implemented method includes using the plurality of threshold gates to perform the linear algebraic calculation in a manner that is simultaneously efficient and at a near constant depth. “Efficient” is defined as a calculation algorithm that uses fewer of the plurality of threshold gates than a naïve algorithm. The naïve algorithm is a straightforward algorithm for solving the linear algebraic calculation. “Constant depth” is defined as an algorithm that has an execution time that is independent of a size of an input to the linear algebraic calculation. The near constant depth comprises a computing depth equal to or between O(log(log(N)) and the constant depth.Type: GrantFiled: September 8, 2017Date of Patent: October 15, 2019Assignee: National Technology & Engineering Solutions of Sandia, LLCInventors: James Bradley Aimone, Ojas D. Parekh, Cynthia A. Phillips
-
Publication number: 20190180169Abstract: A neuromorphic machine and method of determining an optimum value. The neuromorphic machine comprises a plurality of spiking neurons and a plurality of blocking neurons. The plurality of spiking neurons are configured to receive a plurality of input signals representing a plurality of input values and to implement objective functions on the plurality of input values. The plurality of blocking neurons are configured to receive the plurality of input values and output from the plurality of spiking neurons as input and to provide an output signal representing an optimum value corresponding to at least one of the plurality of input values.Type: ApplicationFiled: December 11, 2017Publication date: June 13, 2019Inventors: Stephen Joseph Verzi, Craig Michael Vineyard, Nadine E. Miner, James Bradley Aimone
-
Patent number: 10303697Abstract: A method for processing data is provided. Data is identified by a computer system. The data is processed in parallel by the computer system using temporal transformations to form pieces of temporal data. The pieces of temporal data are placed by the computer system in an order as the pieces of temporal data are generated by the temporal transformations to form a sequence of temporal data. The order of the sequence is based on a priority of when the pieces of temporal data should be processed, enabling performing an action.Type: GrantFiled: June 25, 2015Date of Patent: May 28, 2019Assignees: National Technology & Engineering Solutions of Sandia, LLC, Lewis Rhodes Labs, Inc.Inventors: John H. Naegle, James Bradley Aimone, Frances S. Chance, Craig Michael Vineyard, David R. Follett, Pamela L. Follett