ELECTRONIC CIRCUIT FOR IMPLEMENTING GENERATIVE ADVERSARIAL NETWORK USING SPIKE NEURAL NETWORK

    公开(公告)号:US20190392291A1

    公开(公告)日:2019-12-26

    申请号:US16445925

    申请日:2019-06-19

    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.

    ELECTRODE SELECTION DEVICE FOR SELECTING OPTIMAL ELECTRODES TO COMMUNICATE WITH CAPSULE ENDOSCOPE, AND OPERATION METHOD THEREOF

    公开(公告)号:US20190335984A1

    公开(公告)日:2019-11-07

    申请号:US16402164

    申请日:2019-05-02

    Abstract: Provided is and electrode selection device communicating with a capsule endoscope. The device includes an analog front end configured to recover first data based on first signals transmitted from the capsule endoscope to a first electrode and a second electrode, recover second data based on second signals transmitted from the capsule endoscope to the first electrode and a third electrode, and recover third data based on third signals transmitted from the capsule endoscope to the second electrode and the third electrode, and a digital receiver configured to calculate a first correlation value between the first and second electrodes, a second correlation value between the first and third electrodes, and a third correlation value between the second and third electrodes based on the first to third data. The digital receiver calculates, among the first to third correlation values, a first correlation sum obtained by adding first and second correlation values generated using the first electrode, a second correlation sum obtained by adding the first and third correlation values generated using the second electrode, and a third correlation sum obtained by adding the second and third correlation values generated using the third electrode, and selects a receiving electrode pair among the first to third electrodes based on the first to third correlation sums.

    SPIKING NEURAL NETWORK CIRCUITS GENERATING SPIKE SIGNALS AND METHOD OF OPERATION THEREOF

    公开(公告)号:US20240428047A1

    公开(公告)日:2024-12-26

    申请号:US18422776

    申请日:2024-01-25

    Abstract: Disclosed is a spiking neural network circuit, which includes an axon circuit that generates first and second input spike signals, a synapse circuit that generates a first current based on the first input spike signal and a weight and generates a second current based on the second input spike signal and the weight, a capacitor that forms a first membrane voltage based on the first current, and a neuron circuit including a comparator and that resets the first membrane voltage, and after the capacitor further forms a second membrane voltage based on the second current, and the comparator includes a first input terminal and a second input terminal, receives the first membrane voltage through the first input terminal and a reference voltage through the second input terminal, generates a first spike signal based on a first comparison operation of the first membrane voltage and the reference voltage.

    ENCODER AND OPERATION METHOD THEREOF

    公开(公告)号:US20230125421A1

    公开(公告)日:2023-04-27

    申请号:US17893815

    申请日:2022-08-23

    Abstract: Disclosed is operation method of an encoder that receives a continuous time-series signal and respectively transmits first to N-th input signals to first to N-th input neuron circuits of spike neural network circuit. The method of operating the encoder includes receiving the continuous time-series signal, generating a plurality of discrete quantum signals by sampling and quantizing the continuous time-series signal, selecting first to N-th discrete quantum signals among the plurality of discrete quantum signals, matching the selected first to N-th discrete quantum signals with the first to N-th input neuron circuits, respectively, identifying discrete quantum signals, each of which has a quantum level different from a quantum level of a previous discrete quantum signal, from among the second to N-th discrete quantum signals, and activating the input signals to be transmitted to the input neuron circuits corresponding to the identified discrete quantum signals and the first discrete quantum signal.

    LOW POWER SYSTEM ON CHIP
    40.
    发明申请

    公开(公告)号:US20220413544A1

    公开(公告)日:2022-12-29

    申请号:US17847636

    申请日:2022-06-23

    Abstract: A low power system on chip for supporting partial clock gating is provided. The system on chip includes a network on chip including a first CG-network interface module, a second CG-network interface module, and a clock gating control module, a first IP block that communicates through the first CG-network interface module, and a second IP block that communicates through the second CG-network interface module. The clock gating control module receives a clock gating request from the first IP block, outputs a communication control signal to the second CG-network interface module in response to the received clock gating request, and performs a clock gating operation for a clock signal in response to the received clock gating request to selectively deliver the clock signal to the second IP block.

Patent Agency Ranking