Abstract: An operation method and apparatus for a network layer in a Deep Neural Network are provided. The method includes: acquiring a weighted tensor of the network layer in the Deep Neural Network, the weighted tensor comprising a plurality of filters; converting each filter into a linear combination of a plurality of fixed-point convolution kernels by splitting the filter, wherein a weight value of each of the fixed-point convolution kernels is a fixed-point quantized value having a specified bit-width; for each filter, performing a convolution operation on input data of the network layer and each of the fixed-point convolution kernels, respectively, to obtain a plurality of convolution results, and calculating a weighted sum of the obtained convolution results based on the linear combination of the plurality of fixed-point convolution kernels of the filter to obtain an operation result of the filter; determining output data of the network layer.

Abstract: Disclosed are a hexavalent norovirus VLP vaccine formulation and a preparation method thereof. The formulation comprises six proteins having amino acid sequences shown in SEQ ID No. 2, SEQ ID No. 4, SEQ ID No. 6, SEQ ID No. 8, SEQ ID No. 10, and SEQ ID No. 12. A Pichia pastoris expression system was used to develop the hexavalent norovirus vaccine. Sequencing, digestion, and exogenous gene expression detection were conducted to identify recombinant vectors and select high-expression strains. VLPs were purified by sucrose density gradient centrifugation and identified by electron microscopy, with the results demonstrating that the obtained candidate hexavalent vaccine VLPs had a purity of over 95% and each VLP was intact in structure and uniform in size, indicating structural integrity and stable performance of the VLPs. The hexavalent VLP vaccine induced long-lasting and high-titer antibody responses and generated specific blocking antibodies and T cell immune responses.

Abstract: A deep neural network training method and apparatus and a computer device are provided. The deep neural network training method includes: obtaining task attributes of nodes in a current network layer in a tree-like network topology (S101); performing cluster analysis on the nodes in the current network layer based on the task attributes of the nodes in the current network layer and extracting a common part of task attributes of multiple nodes in a same category as a task attribute for a parent node of the multiple nodes (S102); training a network parameter of each parent node based on a task attribute of this parent node (S103); and determining that training of a deep neural network corresponding to the tree-like network topology is completed, after completion of training of all nodes in all network layers (S104). The operation efficiency of deep learning can be improved through this solution.

Abstract: The embodiments of the present disclosure provides a method and an apparatus for training a neural network model, A training sample is obtained, and the neural network model is trained using the training sample. When the neural network model is trained, power exponential domain fixed-point encoding is performed on a first activation inputted into each network layer and a network weight of each network layer, and an encoded first activation and an encoded network weight are power exponential domain fixed-point data, which when used in the operation, can cause a matrix multiplication operation involved to be converted into an addition operation in the power exponential domain by means of the power exponential domain encoding. The hardware resources required for the addition operation are significantly less than that required for the multiplication operation, which therefore can greatly reduce the hardware resource overhead required for running the neural network model.

Abstract: Embodiments of the present application provide a data storage method, data acquisition method and device thereof. The method includes allocating an N-dimensional first parameter vector for N pieces of to-be-stored data; performing N-dimensional permutation on the first parameter vector, to obtain N second parameter vectors each having N dimensions; constructing a neural network model that maps the current second parameter vectors to expected data samples of the N pieces of to-be-stored data; adjusting model parameters of the neural network model and/or the first parameter vector until expected data samples of the N pieces of to-be-stored data regress to the N pieces of to-be-stored data, the expected data samples being obtained from the current second parameter vectors based on the trained neural network model; storing the current first parameter vector.

Abstract: Embodiments of methods and apparatuses for object detection and of computer devices are disclosed.

Abstract: Embodiments of the present application provide a method, apparatus, and electronic device for eliminating distortion of a distorted image. Side information components of a distorted image are generated. The distorted image is resulted from image processing on an original image. Side information components represent distortion features of the distorted image with respect to original image. Distorted image color components of the distorted image and the side information components are input into a pre-established convolutional neural network model for convolution filtering to obtain distortion-eliminated image color components. The convolutional neural network model is obtained through training based on a preset training set. The training set comprises original sample images, distorted image color components of multiple distorted images corresponding to each of the original sample images, and side information components of each of the distorted images.

Abstract: A deep neural network operation method and apparatus are provided. The method comprises: obtaining an input feature map of a network layer; displacing respectively, according to a preset displacement parameter, each of channels of the input feature map of the network layer along axes, to obtain a displaced feature map, wherein the preset displacement parameter comprises displacement amounts of the channel in the axes; and performing convolution operation on the displaced feature map with a 1×1 convolution kernel to obtain an output feature map of the network layer. The operation efficiency of the DNN can be improved through the above method.

Abstract: The embodiments of the present application provide an image segmentation method, an image segmentation apparatus, and a fully convolutional network system. The method includes: acquiring a target image to be processed; acquiring image feature data of the target image; inputting the image feature data into a pre-trained target network far image segmentation to obtain an output; wherein the target network is a fully convolutional network comprising a hybrid context network structure, and the hybrid context network structure is configured to extract a plurality of reference features at a predetermined scale and fuse them into a target feature that matches a scale of a target object in a segmented image; and wherein the target network is trained with sample images containing target objects at different scales; and obtaining an image segmentation result for the target image based on the output.

Abstract: An operation method and apparatus for a network layer in a Deep Neural Network are provided.

Abstract: Embodiments of the present application provide a method, apparatus, and electronic device for eliminating distortion of a distorted image. Side information components of a distorted image are generated. The distorted image is resulted from image processing on an original image. Side information components represent distortion features of the distorted image with respect to original image. Distorted image color components of the distorted image and the side information components are input into a pre-established convolutional neural network model for convolution filtering to obtain distortion-eliminated image color components. The convolutional neural network model is obtained through training based on a preset training set. The training set comprises original sample images, distorted image color components of multiple distorted images corresponding to each of the original sample images, and side information components of each of the distorted images.

Abstract: Embodiments of the present application disclose a target detection method and device, and relate to the technical field of video processing.

Abstract: A deep neural network training method and apparatus and a computer device are provided. The deep neural network training method includes: obtaining task attributes of nodes in a current network layer in a tree-like network topology (S101); performing cluster analysis on the nodes in the current network layer based on the task attributes of the nodes in the current network layer and extracting a common part of task attributes of multiple nodes in a same category as a task attribute for a parent node of the multiple nodes (S102); training a network parameter of each parent node based on a task attribute of this parent node (S103); and determining that training of a deep neural network corresponding to the tree-like network topology is completed, after completion of training of all nodes in all network layers (S104). The operation efficiency of deep learning can be improved through this solution.

Abstract: Embodiments of methods and apparatuses for object detection and of computer devices are disclosed.

Abstract: Embodiments of the present application disclose a target detection method and device, and relate to the technical field of video processing.

Abstract: The embodiments of the present application provide an image segmentation method, an image segmentation apparatus, and a fully convolutional network system. The method includes: acquiring a target image to be processed; acquiring image feature data of the target image; inputting the image feature data into a pre-trained target network far image segmentation to obtain an output; wherein the target network is a fully convolutional network comprising a hybrid context network structure, and the hybrid context network structure is configured to extract a plurality of reference features at a predetermined scale and fuse them into a target feature that matches a scale of a target object in a segmented image; and wherein the target network is trained with sample images containing target objects at different scales; and obtaining an image segmentation result for the target image based on the output.

Abstract: A multiband antenna includes a plurality of radiation elements, operative within different frequency bands. The multiband microline antenna includes a base substrate that has a signal feeding trace and a partial ground plane, and two or more additional substrates that have multiple microline radiation elements electromagnetically coupled to the signal feeding trace. Each microline radiation element has a width not greater than 0.1 millimeter, and varies in length and resonant frequency. Various disclosed embodiments include a multiband microline folded monopole antenna, a multiband microline loop antenna, a multiband microline inverted-F antenna and a multiband microline ?-shaped antenna.

Abstract: A multiband antenna includes a plurality of radiation elements, operative within different frequency bands. The multiband microline antenna includes a base substrate that has a signal feeding trace and a partial ground plane, and two or more additional substrates that have multiple microline radiation elements electromagnetically coupled to the signal feeding trace. Each microline radiation element has a width not greater than 0.1 millimeter, and varies in length and resonant frequency. Various disclosed embodiments include a multiband microline folded monopole antenna, a multiband microline loop antenna, a multiband microline inverted-F antenna and a multiband microline ?-shaped antenna.

Abstract: A “Universal Rate Control Mechanism with Parameter Adaptation” (URCMPA) improves real-time communication (RTC) sessions in terms of delay, loss, throughput, and PSNR. The URCMPA automatically learns network characteristics including bottleneck link capacity, inherent queuing delay, inherent packet loss rates, etc., during RTC sessions. The URCMPA uses this information to dynamically adapt rate control parameters in a utility maximization (UM) framework. The URCMPA operates reliable RTC sessions across a wide range and combination of networks near full throughput rates while maintaining low operating congestion levels (e.g., low queuing delay and low packet loss). Examples of networks applicable for use with the URCMPA include, but are not limited to, combinations of mobile broadband (e.g., 3G, 4G, etc.), WiMAX, Wi-Fi hotspots, etc., and physical networks based on cable, fiber, ADSL, etc.