公开(公告)号：US11954579B2

公开(公告)日：2024-04-09

申请号：US18265715

申请日：2022-05-31

Applicant: LYNXI TECHNOLOGIES CO., LTD.

Inventor： Zhenzhi Wu ,  Xin Ma ,  Qune Kong ,  Yaolong Zhu

IPC: G06N3/049 ,  G06N3/084

CPC classification number: G06N3/049 ,  G06N3/084

Abstract: The present disclosure relates to a synaptic weight training method, a target identification method, an electronic device and a storage medium. The synaptic weight training method includes: inputting spike signals corresponding to training samples into a spiking neural network to be trained; learning a target synaptic weight in the spiking neural network with a back propagation rule to obtain a first branch weight; and learning the target synaptic weight with a synaptic plasticity rule to obtain a second branch weight; and updating the target synaptic weight according to the first branch weight and the second branch weight.

公开(公告)号：US11769044B2

公开(公告)日：2023-09-26

申请号：US17642266

申请日：2020-10-27

Applicant: LYNXI TECHNOLOGIES CO., LTD.

Inventor： Weihao Zhang ,  Han Li ,  Chuan Hu ,  Yaolong Zhu

IPC: G06N3/063

CPC classification number: G06N3/063

Abstract: A neural network mapping method and a neural network mapping apparatus are provided. The method includes: mapping a calculation task for a preset feature map of each network layer in a plurality of network layers in a convolutional neural network to at least one processing element of a chip; acquiring the number of phases needed by a plurality of processing elements in the chip for completing the calculation tasks, and performing a first stage of balancing on the number of phases of the plurality of processing elements; and based on the number of the phases of the plurality of processing elements obtained after the first stage of balancing, mapping the calculation task for the preset feature map of each network layer in the plurality of network layers in the convolutional neural network to at least one processing element of the chip subjected to the first stage of balancing.

公开(公告)号：US20230040375A1

公开(公告)日：2023-02-09

申请号：US17760023

申请日：2021-06-09

Applicant: LYNXI TECHNOLOGIES CO., LTD.

Inventor： Fanhui MENG ,  Chuan HU ,  Han LI ,  Xinyang WU ,  Yaolong ZHU

IPC: G06N3/063 ,  G06F9/50

Abstract: Disclosed are a network accuracy quantification method, system, and device, an electronic device and a readable medium, which are applicable to a many-core chip. The method includes: determining a reference accuracy according to a total core resource number of the many-core chip and the number of core resources required by each network to be quantified, with the number of the core resources required by each network to be quantified being the number of the core resources which is determined after each network to be quantified is quantified; and determining a target accuracy corresponding to each network to be quantified according to the reference accuracy and the total core resource number of the many-core chip.

公开(公告)号：US20220417169A1

公开(公告)日：2022-12-29

申请号：US17778929

申请日：2020-12-09

Applicant: LYNXI TECHNOLOGIES CO., LTD.

Inventor： Yangshu SHEN ,  Yaolong ZHU

IPC: H04L47/6275 ,  H04L49/109 ,  H04L47/62

Abstract: Provided in the present disclosure are a data processing method and apparatus, and an electronic device, the method includes: determining a plurality of candidate data pieces, where the candidate data pieces are provided from corresponding data sources; and determining a target data piece based on priorities of the data sources corresponding to the plurality of candidate data pieces in a current cycle, wherein a same data source has different priorities in different processing cycles, and priority sequence numbers of a same data source in different processing cycles satisfy a nonlinear relationship.

公开(公告)号：US20220318608A1

公开(公告)日：2022-10-06

申请号：US17642266

申请日：2020-10-27

Applicant: LYNXI TECHNOLOGIES CO., LTD.

Inventor： Weihao ZHANG ,  Han LI ,  Chuan HU ,  Yaolong ZHU

IPC: G06N3/063

Abstract: A neural network mapping method and a neural network mapping apparatus are provided. The method includes: mapping a calculation task for a preset feature map of each network layer in a plurality of network layers in a convolutional neural network to at least one processing element of a chip; acquiring the number of Phases needed by a plurality of processing elements in the chip for completing the calculation tasks, and performing a first stage of balancing on the number of Phases of the plurality of processing elements; and based on the number of the Phases of the plurality of processing elements obtained after the first stage of balancing, mapping the calculation task for the preset feature map of each network layer in the plurality of network layers in the convolutional neural network to at least one processing element of the chip subjected to the first stage of balancing.

公开(公告)号：US20240118932A1

公开(公告)日：2024-04-11

申请号：US18276372

申请日：2022-01-20

Applicant: LYNXI TECHNOLOGIES CO., LTD

Inventor： Zhenzhi WU ,  Ruiqiang DING ,  Wei HE

IPC: G06F9/50

CPC classification number: G06F9/5038

Abstract: Provided are a signal processing method based on a many-core chip, an electronic device and a medium. The method includes: determining, according to a time domain signal to be processed and a time-frequency transform type of the time domain signal, a transform kernel matrix of the time domain signal; mapping the transform kernel matrix to a plurality of processing cores of the many-core chip; and mapping the time domain signal to the plurality of processing cores so that the plurality of processing cores determine, according to the transform kernel matrix and the time domain signal, a frequency domain signal corresponding to the time domain signal.

公开(公告)号：US11941526B2

公开(公告)日：2024-03-26

申请号：US18004013

申请日：2021-12-28

Applicant: LYNXI TECHNOLOGIES CO., LTD.

Inventor： Zhenzhi Wu ,  Qikun Zhang ,  Yaolong Zhu

IPC: G06N3/08 ,  G06N3/049

CPC classification number: G06N3/08 ,  G06N3/049

Abstract: Provided is a method for training spiking neuron network, including: inputting a spiking signal corresponding to a training sample into a spiking neuron network to be trained; and training the spiking neuron network based on a back propagation rule, wherein a forward propagation stage of training includes: adjusting a spiking firing threshold corresponding to a target layer in the spiking neuron network according to confidence corresponding to the target layer. Also provided are a method for processing data based on a spiking neuron network, an electronic device, and a non-transitory computer-readable medium.

公开(公告)号：US11847091B2

公开(公告)日：2023-12-19

申请号：US17418348

申请日：2019-11-28

Applicant: LYNXI TECHNOLOGIES CO., LTD.

Inventor： Yangshu Shen ,  Luping Shi ,  Yaolong Zhu

IPC: G06F15/78

CPC classification number: G06F15/7825

Abstract: The present disclosure provides a data transmission method and device for a network on chip and an electronic apparatus. The method includes: receiving, by a second network node, a first data packet sent by a first network node, the first data packet including first identification information and a data packet payload; determining, by the second network node, valid transmission information and second identification information corresponding to the valid transmission information according to the first identification information; determining, by the second network node, a second data packet according to the second identification information and the data packet payload; and sending, by the second network node, the second data packet according to the valid transmission information.

公开(公告)号：US20230196197A1

公开(公告)日：2023-06-22

申请号：US18004021

申请日：2021-07-23

Applicant: LYNXI TECHNOLOGIES CO., LTD.

Inventor： Han LI ,  Yaolong ZHU

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A calibration method, a calibration apparatus, a terminal device and a storage medium are provided. The method comprises the following steps: determining layer attribute information of each to-be-calibrated layer in a model (S110); and determining the group in which each of the to-be-calibrated layers is located according to the total available resources and the layer attribute information of each of the to-be-calibrated layers (S120). The layer attribute information of any of the to-be-calibrated layers comprises layer required resources, the layer required resources are resources needing to be occupied when the to-be-calibrated layer is calibrated; and the total available resources are the total resources used for calibration. By means of the method, all of to-be-calibrated layers can be reasonably grouped on the premise that the total available resources can provide support, so that the layer required resources in each calibration operation are balanced and large as much as possible, thereby making full use of resources. Moreover, the number of calibration operations is reduced, and the calculation speed during the calibration of a model is increased.

公开(公告)号：US11461626B2

公开(公告)日：2022-10-04

申请号：US17431479

申请日：2020-01-15

Applicant: LYNXI TECHNOLOGIES CO., LTD.

Inventor： Zhenzhi Wu ,  Guanrui Wang ,  Luping Shi ,  Yaolong Zhu

IPC: G06N3/063 ,  G06F7/544

Abstract: The present disclosure provides a brain-like computing chip and a computing device. The brain-like computing chip includes is a many-core system composed of one or more functional cores, and data transmission is performed between the functional cores by means of a network-on-chip. The functional core includes at least one neuron processor configured to compute various neuron models, and at least one coprocessor coupled to the neuron processor and configured to perform an integral operation and/or a multiply-add-type operation; and the neuron processor is capable of calling the coprocessor to perform the multiply-add-type operation.