Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

72 results about "Memory code" patented technology

Structured memory graph network model for multiple rounds of spoken language understanding

The invention discloses a structured memory graph network model for multiple rounds of spoken language understanding, which is composed of an input coding layer, a memory coding layer, a feature aggregation layer and an output classification layer, dialogue behaviors generated by spoken language understanding tasks are used to replace texts as memory nodes for coding, and the dialogue behaviors are formatted representations containing semantic framework information. And the unstructured characters are converted into a structured triple. A graph attention network is used for replacing a recurrent neural network and an attention mechanism to achieve feature aggregation, sequence information between the attention mechanism and dialogue nodes is reserved, and model learning how to effectivelyutilize structured memory nodes is facilitated. According to the network model, the encoding dialogue behavior replaces a historical dialogue text to serve as a memory unit, original information of asemantic framework is reserved to the maximum extent, and the problems that in the prior art, noise is generated in complex occasions due to the fact that text information depends on a model, and operation efficiency is low are solved.
Owner:NORTHWEST NORMAL UNIVERSITY

Fast memory coding method and device based on multi-synaptic plasticity spiking neural network

The invention provides a fast memory coding method based on a multi-synaptic plasticity pulse neural network. The fast memory coding method comprises the steps of 1, converting external stimulation into an input pulse sequence based on a hierarchical coding strategy; 2, after the pulse neural network receives an input pulse, updating a membrane potential of neurons of an output layer based on an improved SRM model; 3, updating a synaptic weight input to an output layer by using a supervisory group Tempotron, and activating neuron memory input of the output layer; step 4, after the neurons of the output layer are activated, using the unsupervised STDP to update synaptic weights among the activated neurons in the layer, and forming an enhanced cyclic sub-network storage memory; and step 5, while executing the step 4, using unsupervised inhibition synaptic plasticity, updating a synaptic weight between an inhibition layer and an output layer, and inhibiting separation of distribution time of neural populations with different inputs of feedback guarantee memories. The invention further provides a fast memory coding device based on the multi-synaptic plastic spiking neural network. According to the invention, the coding speed and stability of memory are effectively improved.
Owner:ZHEJIANG LAB +1

SRAM memory cell and circuit for improving read/write stability of SRAM memory cell

The invention relates to the technical field of electronic communication, in particular to an SRAM memory cell and a circuit for improving the read/write stability of the SRAM memory cell. The SRAM memory cell comprises a first switch device, a second switch device, a first inverse unit and a second inverse unit, wherein the first switch device is controllably connected with a first bit line to a first memory code; the second switch device is controllably connected with a second bit line to a second memory code; the first inverse unit is connected between the first switch device and the second switch device in series; the first inverse unit is provided with a first input end and a first output end; the first memory code is defined at the first output end; the second inverse unit is connected between the first switch device and the second switch device in series; a second input end of the second inverse unit is connected with the first output end; a second output end of the second inverse unit is connected with the first input end; and the second memory code is defined at the second output end. According to the SRAM memory cell and the circuit, better read/write ability is provided, the reliability of the SRAM memory cell is improved without adding overmuch extra circuits, the complexity of circuit design is reduced and the area is saved.
Owner:SPREADTRUM COMM (SHANGHAI) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products