Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

2results about How to "Prevent disappearing" patented technology

Training method for spiking neural networks, spiking neural networks and devices

This application provides a training method, a spiking neural network, and an apparatus for a spiking neural network. The method includes: iteratively training the spiking neural network using training data of the object to be processed, wherein the spiking neural network contains at least one neuron model; calculating a task loss function based on the training results of the spiking neural network and updating the weight parameters; updating the current discharge threshold parameter of the neuron model based on the historical discharge frequency of the neuron model, wherein the value of the current discharge threshold parameter increases with the increase of the historical discharge frequency; and obtaining the trained spiking neural network model using the updated weight parameters and the updated discharge threshold parameter after multiple iterations of training. This method facilitates the training of a sparsely discharging spiking neural network, reduces the energy consumption during spiking neural network applications, and improves model energy efficiency by using the trained spiking neural network model to process the data of the object to be processed.
Owner:PEKING UNIV

HUD virtual image and real environment polarization matching detection method

ActiveCN122089726AEnsure visual consistencyavoid darkeningImage analysisPolarisation-affecting propertiesEngineeringThresholding
The invention discloses an HUD virtual image and real environment polarization matching detection method. The method comprises the following steps: when an HUD projects a virtual image, collecting a virtual polarization parameter set of a plurality of preset test points in an HUD virtual image picture; synchronously acquiring a real environment polarization parameter set of real environment light in corresponding directions of the plurality of preset test points; inputting the virtual polarization parameter set and the real environment polarization parameter set into a preset polarization matching degree evaluation model, and calculating a matching degree score of each preset test point; when at least one of the matching degree scores of the preset test points is lower than a preset threshold value, it is judged that the test points have polarization conflicts, and polarization conflict types and conflict position information are output. According to the method and the device, the visibility of the virtual image under the polarized sunglasses and the visual consistency of the virtual image and the real ambient light are ensured, so that the darkening, disappearance, glare and visual fatigue of the image are avoided, and the driving safety and the user experience are remarkably improved.
Owner:SUZHOU METROLOGY & TESTING INSTITUTE CO LTD