A data processing method includes: obtaining to-be-processed data and a target neural network model, where the target neural network model includes a first transformer layer, the first transformer layer includes a first residual branch and a second residual branch, the first residual branch includes a first attention head, and the second residual branch includes a target feed-forward network (FFN) layer; and performing target task related processing on the to-be-processed data based on the target neural network model, to obtain a data processing result, where the target neural network model is for performing a target operation on an output of the first attention head and a first weight value to obtain an output of the first residual branch, and/or the target neural network model is for performing a target operation on an output of the target FFN and a second weight value to obtain an output of the second residual branch.

A method for diagnostic imaging reconstruction uses a prior image x.sup.pr from a scan of a subject to initialize parameters of a neural network which maps coordinates in image space to corresponding intensity values in the prior image. The parameters are initialized by minimizing an objective function representing a difference between intensity values of the prior image and predicted intensity values output from the neural network. The neural network is then trained using subsampled (sparse) measurements of the subject to learn a neural representation of a reconstructed image. The training includes minimizing an objective function representing a difference between the subsampled measurements and a forward model applied to predicted image intensity values output from the neural network. Image intensity values output from the trained neural network from coordinates in image space input to the trained neural network are computed to produce predicted image intensity values.

The present disclosure relates to processing input data by a neural network. Methods and apparatuses of some embodiments process the input data by at least one layer of the neural network and obtain thereby a feature tensor. Then, the distribution of the obtained feature tensors estimated. Another distribution is obtained. Such other distribution may be a distribution of another input data, or a distribution obtained by combining a plurality of distributions obtained for respective plurality of some input data. Then a distance value indicative of a distance between the two distributions is calculated and based thereon, a characteristic of the input data is determined. The characteristic may be pertinence to a certain class of data or a detection of out-of-distribution data or determination of reliability of a class determination or the like.

The present disclosure relates to processing input data by a neural network. Methods and apparatuses of some embodiments process the input data by at least one layer of the neural network and obtain thereby a feature tensor. Then, the distribution of the obtained feature tensors estimated. Another distribution is obtained. Such other distribution may be a distribution of another input data, or a distribution obtained by combining a plurality of distributions obtained for respective plurality of some input data. Then a distance value indicative of a distance between the two distributions is calculated and based thereon, a characteristic of the input data is determined. The characteristic may be pertinence to a certain class of data or a detection of out-of-distribution data or determination of reliability of a class determination or the like.

Disclosed are techniques for wireless positioning. In an aspect, a first user equipment (UE) obtains one or more first radio frequency fingerprint (RFFP) measurements of one or more first downlink channels received at the first UE, one or more first sidelink channels received at the first UE, or both, and determines one or more locations of a target UE based on the one or more first RFFP measurements and a machine learning module, wherein the machine learning module is trained based on previously collected RFFP measurements of one or more downlink channels, RFFP measurements of one or more uplink channels, RFFP measurements of one or more sidelink channels, locations of one or more sidelink anchor UEs, locations of one or more base stations, or any combination thereof.

To provide an electronic device capable of recognizing a user's emotion with a high accuracy. The electronic device includes a detection device, an arithmetic device, and a housing. The housing includes a space at a position overlapping with a user's nose when the user wears the electronic device. The detection device is located between the housing and the user's nose. The detection device has a function of obtaining user's data on an emotion of the user and outputting the user's data to the arithmetic device. The arithmetic device has a function of generating display data based on the user's data and outputting the display data.

An electronic apparatus performs a method of recovering a complete and dense point cloud from a partial point cloud. The method includes: constructing a sparse but complete point cloud from the partial point cloud through a contrastive teacher-student neural network; and transforming the sparse but complete point cloud to the complete and dense point cloud. In some embodiments, the contrastive teacher-student neural network has a dual network structure comprising a teacher network and a student network both sharing the same architecture. The teacher network is a point cloud self-reconstruction network, and the student network is a point cloud completion network.

A data model identifying a first and second table may be stored, the first table comprising a first and second attribute, the second table comprising a third attribute. A first filter parameter of a first filter and a second filter parameter of a second filter may be obtained. A first tag value may be associated with the first and second filters. A set of filters including the first and second filters may be determined in response to a determination that the first and second filters are associated with the first tag value. An argument indicating the first and second filter parameters may be generated based on the set of filters. A call to the first table may be executed based on the argument, the execution of the call causing values of the first and second attributes to be obtained based on the first and second filter parameters.

A method and a system for using a graph neural network framework to implement a link prediction in a multiplex network environment is provided. The method includes: identifying a plurality of layers of a multiplex network, each respective layer including a respective plurality of nodes; for each node included in at least a first layer, providing, by a structural node label and determining a common embedding across all of the plurality of layers and an individual embedding for each individual layer; using a k-nearest approach to select a subset of the plurality of layers for performing link prediction with respect to each layer based on the determined embeddings; and performing a link prediction by determining a respective feed-forward network with respect to each layer included in the selected subset.

A method and a system for using a graph neural network framework to implement a link prediction in a multiplex network environment is provided. The method includes: identifying a plurality of layers of a multiplex network, each respective layer including a respective plurality of nodes; for each node included in at least a first layer, providing, by a structural node label and determining a common embedding across all of the plurality of layers and an individual embedding for each individual layer; using a k-nearest approach to select a subset of the plurality of layers for performing link prediction with respect to each layer based on the determined embeddings; and performing a link prediction by determining a respective feed-forward network with respect to each layer included in the selected subset.