Search Patents
  • ARTIFICIAL NEURAL NETWORK DEVICE AND OPERATION METHOD THEREOF
    Publication number: 20180225563
    Abstract: Provided is an artificial neural network device including pre-synaptic neurons configured to generate a plurality of input spike signals, and a post-synaptic neuron configured to receive the plurality of input spike signals and to generate an output spike signal during a plurality of time periods, wherein the post-synaptic neuron respectively applies different weights in the plurality of time periods according to contiguousness with a reference time period in which input spike signals, which lead generation of the output spike signal from among the plurality of input spike signals, are received.
    Type: Application
    Filed: January 11, 2018
    Publication date: August 9, 2018
    Inventors: Ju-Yeob KIM, Byung Jo KIM, Jin Kyu KIM, Mi Young LEE, Seong Min KIM, Joo Hyun LEE
  • Neuromorphic training algorithm for a Restricted Boltzmann Machine
    Patent number: 10510001
    Abstract: This invention solves the long-standing problem in Machine Learning of training a neural network on a spike-based neuromorphic computer. The preferred embodiment of the invention describes an algorithm for training a Restricted Boltzmann Machine (RBM) neural network, but the invention applies equally to training neural networks in the general class of Markov Random Fields. The standard CD algorithm for training an RBM on a general-purpose computer is unsuitable for implementation on a neuromorphic computer, as it requires the communication of real-valued parameter values between neurons, and/or shared memory access by neurons to stored parameter values. By employing the invention described, these requirements are eliminated, thus providing a training algorithm which can be implemented efficiently on a spike-based, distributed processor and memory, neuromorphic computer system.
    Type: Grant
    Filed: March 17, 2017
    Date of Patent: December 17, 2019
    Assignee: Mindtrace Limited
    Inventor: Michael James Denham
  • NEUROMORPHIC EVENT-DRIVEN NEURAL COMPUTING ARCHITECTURE IN A SCALABLE NEURAL NETWORK
    Publication number: 20130073497
    Abstract: An event-driven neural network includes a plurality of interconnected core circuits is provided. Each core circuit includes an electronic synapse array has multiple digital synapses interconnecting a plurality of digital electronic neurons. A synapse interconnects an axon of a pre-synaptic neuron with a dendrite of a post-synaptic neuron. A neuron integrates input spikes and generates a spike event in response to the integrated input spikes exceeding a threshold. Each core circuit also has a scheduler that receives a spike event and delivers the spike event to a selected axon in the synapse array based on a schedule for deterministic event delivery.
    Type: Application
    Filed: September 16, 2011
    Publication date: March 21, 2013
    Applicants: Cornell University, INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Filipp Akopyan, John V. Arthur, Rajit Manohar, Paul A. Merolla, Dharmendra S. Modha, Alyosha Molnar, William P. Risk, III
  • PERFORMING PROCESSING-IN-MEMORY OPERATIONS RELATED TO PRE-SYNAPTIC SPIKE SIGNALS, AND RELATED METHODS AND SYSTEMS
    Publication number: 20240273349
    Abstract: Spiking events in a spiking neural network may be processed via a memory system. A memory system may store data corresponding to a group of destination neurons. The memory system may, at each time interval of a SNN, pass through data corresponding to a group of pre-synaptic spike events from respective source neurons. The data corresponding to the group of pre-synaptic spike events may be subsequently stored in the memory system.
    Type: Application
    Filed: April 22, 2024
    Publication date: August 15, 2024
    Inventors: Dmitri Yudanov, Sean S. Eilert, Hernan A. Castro, Ameen D. Akel
  • CIRCUIT AND METHOD FOR SPIKE TIME DEPENDENT PLASTICITY
    Publication number: 20220147796
    Abstract: The present disclosure relates to a neuron circuit of a spiking neural network comprising: a first resistive switching memory device having a conductance that decays over time; and a programming circuit configured to reset the resistive state of the first resistive switching element in response to a spike in an output voltage of the neuron circuit.
    Type: Application
    Filed: November 10, 2021
    Publication date: May 12, 2022
    Inventors: Thomas DALGATY, Elisa VIANELLO, Filippo MORO, Giacomo INDIVERI, Melika PAYVAND
  • Performing processing-in-memory operations related to pre-synaptic spike signals, and related methods and systems
    Patent number: 12008460
    Abstract: Spiking events in a spiking neural network may be processed via a memory system. A memory system may store data corresponding to a group of destination neurons. The memory system may, at each time interval of a SNN, pass through data corresponding to a group of pre-synaptic spike events from respective source neurons. The data corresponding to the group of pre-synaptic spike events may be subsequently stored in the memory system.
    Type: Grant
    Filed: August 31, 2020
    Date of Patent: June 11, 2024
    Assignee: Micron Technology, Inc.
    Inventors: Dmitri Yudanov, Sean S. Eilert, Hernan A. Castro, Ameen D. Akel
  • NEUROMORPHIC EVENT-DRIVEN NEURAL COMPUTING ARCHITECTURE IN A SCALABLE NEURAL NETWORK
    Publication number: 20160224886
    Abstract: An event-driven neural network includes a plurality of interconnected core circuits is provided. Each core circuit includes an electronic synapse array has multiple digital synapses interconnecting a plurality of digital electronic neurons. A synapse interconnects an axon of a pre-synaptic neuron with a dendrite of a post-synaptic neuron. A neuron integrates input spikes and generates a spike event in response to the integrated input spikes exceeding a threshold. Each core circuit also has a scheduler that receives a spike event and delivers the spike event to a selected axon in the synapse array based on a schedule for deterministic event delivery.
    Type: Application
    Filed: January 6, 2016
    Publication date: August 4, 2016
    Inventors: Filipp Akopyan, John V. Arthur, Paul A. Merolla, Dharmendra S. Modha, William P. Risk
  • APPARATUS AND METHODS FOR REINFORCEMENT LEARNING IN ARTIFICIAL NEURAL NETWORKS
    Publication number: 20130325776
    Abstract: Neural network apparatus and methods for implementing reinforcement learning. In one implementation, the neural network is a spiking neural network, and the apparatus and methods may be used for example to enable an adaptive signal processing system to effect focused exploration by associative adaptation, including providing a negative reward signal to the network, which may increase excitability of the neurons in combination with decrease in excitability of active neurons. In certain implementations, the increase is gradual and of smaller magnitude, compared to the excitability decrease. In some implementations, the increase/decrease of the neuron excitability is effectuated by increasing/decreasing an efficacy of the respective synaptic connections delivering presynaptic inputs into the neuron. The focused exploration may be achieved for instance by non-associative potentiation configured based at least on the input spike rate.
    Type: Application
    Filed: June 5, 2012
    Publication date: December 5, 2013
    Inventors: Filip Ponulak, Oleg Sinyavskiy
  • Apparatus and methods for reinforcement learning in artificial neural networks
    Patent number: 8943008
    Abstract: Neural network apparatus and methods for implementing reinforcement learning. In one implementation, the neural network is a spiking neural network, and the apparatus and methods may be used for example to enable an adaptive signal processing system to effect focused exploration by associative adaptation, including providing a negative reward signal to the network, which may increase excitability of the neurons in combination with decrease in excitability of active neurons. In certain implementations, the increase is gradual and of smaller magnitude, compared to the excitability decrease. In some implementations, the increase/decrease of the neuron excitability is effectuated by increasing/decreasing an efficacy of the respective synaptic connections delivering presynaptic inputs into the neuron. The focused exploration may be achieved for instance by non-associative potentiation configured based at least on the input spike rate.
    Type: Grant
    Filed: June 5, 2012
    Date of Patent: January 27, 2015
    Assignee: Brain Corporation
    Inventors: Filip Ponulak, Oleg Sinyavskiy
  • Spike domain and pulse domain non-linear processors
    Patent number: 7822698
    Abstract: A neural network has an array of interconnected processors, each processor operating either the pulse domain or spike domain.
    Type: Grant
    Filed: March 23, 2007
    Date of Patent: October 26, 2010
    Assignee: HRL Laboratories, LLC
    Inventors: Jose Cruz-Albrecht, Peter Petre
  • SPIKING NEURAL NETWORK CIRCUIT INCLUDING DOUBLE PRECISION ASYNCHRONOUS NEURONS AND METHOD OF OPERATION THEREOF
    Publication number: 20240378429
    Abstract: Disclosed is a spiking neural network circuit, which includes an axon circuit that generates an input spike signal, a synapse circuit that outputs a current based on the input spike signal and a weight, a capacitor that forms a membrane voltage based on the current, and a neuron circuit that generates an output spike signal based on the membrane voltage, and the neuron circuit includes a first comparator that generates an intermediate spike signal based on the membrane voltage and a first reference voltage, and a second comparator that generates the output spike signal based on the intermediate spike signal, the membrane voltage, and a second reference voltage that is different from the first reference voltage.
    Type: Application
    Filed: January 8, 2024
    Publication date: November 14, 2024
    Inventors: Kwang IL OH, Tae Wook KANG, Hyuk KIM, Jae-Jin LEE
  • Continuous time spiking neural network event-based simulation that schedules co-pending events using an indexable list of nodes
    Patent number: 9015096
    Abstract: Certain aspects of the present disclosure provide methods and apparatus for a continuous-time neural network event-based simulation that includes a multi-dimensional multi-schedule architecture with ordered and unordered schedules and accelerators to provide for faster event sorting; and a formulation of modeling event operations as anticipating (the future) and advancing (update/jump ahead/catch up) rules or methods to provide a continuous-time neural network model. In this manner, the advantages include faster simulation of spiking neural networks (order(s) of magnitude); and a method for describing and modeling continuous time neurons, synapses, and general neural network behaviors.
    Type: Grant
    Filed: May 30, 2012
    Date of Patent: April 21, 2015
    Assignee: QUALCOMM Incorporated
    Inventor: Jason Frank Hunzinger
  • GLOBAL AND LOCAL TIME-STEP DETERMINATION SCHEMES FOR NEURAL NETWORKS
    Publication number: 20190102669
    Abstract: In one embodiment, a processor comprises a first neuromorphic core to implement a plurality of neural units of a neural network, the first neuromorphic core comprising a memory to store a current time-step of the first neuromorphic core; and a controller to track current time-steps of neighboring neuromorphic cores that receive spikes from or provide spikes to the first neuromorphic core; and control the current time-step of the first neuromorphic core based on the current time-steps of the neighboring neuromorphic cores.
    Type: Application
    Filed: September 29, 2017
    Publication date: April 4, 2019
    Inventors: Gregory K. Chen, Kshitij Bhardwaj, Raghavan Kumar, Huseyin E. Sumbul, Phil Knag, Ram K. Krishnamurthy, Himanshu Kaul
  • ELECTRONIC CIRCUIT FOR IMPLEMENTING GENERATIVE ADVERSARIAL NETWORK USING SPIKE NEURAL NETWORK
    Publication number: 20190392291
    Abstract: Provided is an electronic circuit for implementing a generative adversarial neural network. The electronic circuit includes a spike converter, a spike image generator, a spike image converter, and an image discriminator. The spike converter generates a first signal including spike signals. The number of the spike signals is determined based on first data associated with second data within a reference time interval. The spike image generator generates a second signal including spike signals being selected based on a weight among the spike signals of the first signal. The image converter converts the spike signals of the second signal to generate third data being represented in an analog domain. The image discriminator provides the spike image generator with result data being associated with a difference between a value of the third data and a value of the second data. The image generator determines the weight based on the result data.
    Type: Application
    Filed: June 19, 2019
    Publication date: December 26, 2019
    Applicant: Electronics and Telecommunications Research Institute
    Inventors: Seong Mo PARK, Jae-Jin LEE, Sung Eun KIM, Kyung Hwan PARK, Mi Jeong PARK, Young Hwan BAE, Kwang IL OH, Byounggun CHOI
  • CONTINUOUS TIME SPIKING NEURAL NETWORK EVENT-BASED SIMULATION
    Publication number: 20130325765
    Abstract: Certain aspects of the present disclosure provide methods and apparatus for a continuous-time neural network event-based simulation that includes a multi-dimensional multi-schedule architecture with ordered and unordered schedules and accelerators to provide for faster event sorting; and a formulation of modeling event operations as anticipating (the future) and advancing (update/jump ahead/catch up) rules or methods to provide a continuous-time neural network model. In this manner, the advantages include faster simulation of spiking neural networks (order(s) of magnitude); and a method for describing and modeling continuous time neurons, synapses, and general neural network behaviors.
    Type: Application
    Filed: May 30, 2012
    Publication date: December 5, 2013
    Applicant: QUALCOMM Incorporated
    Inventor: Jason Frank Hunzinger
  • Neural network architecture
    Patent number: 11501150
    Abstract: Various implementations are related to an apparatus with memory cells arranged in columns and rows, and the memory cells are accessible with a column control voltage for accessing the memory cells via the columns and a row control voltage for accessing the memory cells via the rows. The apparatus may include neural network circuitry having neuronal junctions that are configured to receive, record, and provide information related to incoming voltage spikes associated with input signals based on resistance through the neuronal junctions. The apparatus may include stochastic re-programmer circuitry that receives the incoming voltage spikes, receives the information provided by the neuronal junctions, and reconfigure the information recorded in the neuronal junctions based on the incoming voltage spikes associated with the input signals along with a programming control signal provided by the memory circuitry.
    Type: Grant
    Filed: May 20, 2020
    Date of Patent: November 15, 2022
    Assignee: Arm Limited
    Inventors: Mbou Eyole, Shidhartha Das, Fernando Garcia Redondo
  • Neural Network Architecture
    Publication number: 20210365764
    Abstract: Various implementations are related to an apparatus with memory cells arranged in columns and rows, and the memory cells are accessible with a column control voltage for accessing the memory cells via the columns and a row control voltage for accessing the memory cells via the rows. The apparatus may include neural network circuitry having neuronal junctions that are configured to receive, record, and provide information related to incoming voltage spikes associated with input signals based on resistance through the neuronal junctions. The apparatus may include stochastic re-programmer circuitry that receives the incoming voltage spikes, receives the information provided by the neuronal junctions, and reconfigure the information recorded in the neuronal junctions based on the incoming voltage spikes associated with the input signals along with a programming control signal provided by the memory circuitry.
    Type: Application
    Filed: May 20, 2020
    Publication date: November 25, 2021
    Inventors: Mbou Eyole, Shidhartha Das, Femando Garcia Redondo
  • Event-based extraction of features in a convolutional spiking neural network
    Patent number: 11989645
    Abstract: A system is described that comprises a memory for storing data representative of at least one kernel, a plurality of spiking neuron circuits, and an input module for receiving spikes related to digital data. Each spike is relevant to a spiking neuron circuit and each spike has an associated spatial coordinate corresponding to a location in an input spike array. The system also comprises a transformation module configured to transform a kernel to produce a transformed kernel having an increased resolution relative to the kernel, and/or transform the input spike array to produce a transformed input spike array having an increased resolution relative to the input spike array.
    Type: Grant
    Filed: January 25, 2022
    Date of Patent: May 21, 2024
    Assignee: BrainChip, Inc.
    Inventors: Douglas McLelland, Kristofor D. Carlson, Harshil K. Patel, Anup A. Vanarse, Milind Joshi
  • TARGET TRACKING METHOD AND SYSTEM OF SPIKING NEURAL NETWORK BASED ON EVENT CAMERA
    Publication number: 20230410328
    Abstract: A target tracking method and a target tracking system of a spiking neural network based on an event camera are provided. The method includes: acquiring a data stream of asynchronous events in a high dynamic scene of a target by an event camera as input data; dividing the data stream of the asynchronous events into synchronous event frames with millisecond time resolution; training a twin network based on a spiking neural network by a gradient substitution algorithm with a target image as a template image and a complete image as a searched image; and tracking the target by a trained twin network with interpolating a result of feature mapping to up-sample and obtaining the position of the target in an original image. The twin network includes a feature extractor and a cross-correlation calculator.
    Type: Application
    Filed: August 31, 2023
    Publication date: December 21, 2023
    Inventors: Wenyi ZHAO, Huajin TANG, Chaofei HONG, Xiao WANG, Mengwen YUAN, Yujing LU, Mengxiao ZHANG, Gang PAN
  • ACOUSTIC SYSTEM AND METHOD BASED GESTURE DETECTION USING SPIKING NEURAL NETWORKS
    Publication number: 20230325001
    Abstract: Conventional gesture detection approaches demand large memory and computation power to run efficiently, thus limiting their use in power and memory constrained edge devices. Present application/disclosure provides a Spiking Neural Network based system which is a robust low power edge compatible ultrasound-based gesture detection system. The system uses a plurality of speakers and microphones that mimics a Multi Input Multi Output (MIMO) setup thus providing requisite diversity to effectively address fading. The system also makes use of distinctive Channel Impulse Response (CIR) estimated by imposing sparsity prior for robust gesture detection. A multi-layer Convolutional Neural Network (CNN) has been trained on these distinctive CIR images and the trained CNN model is converted into an equivalent Spiking Neural Network (SNN) via an ANN (Artificial Neural Network)-to-SNN conversion mechanism. The SNN is further configured to detect/classify gestures performed by user(s).
    Type: Application
    Filed: December 14, 2022
    Publication date: October 12, 2023
    Applicant: Tata Consultancy Services Limited
    Inventors: ANDREW GIGIE, ARUN GEORGE, ACHANNA ANIL KUMAR, SOUNAK DEY, ARPAN PAL
Narrow Results

Filter by US Classification