Abstract: A connector for connecting at a proximal end of the connector along a connection direction includes a contact section adapted to fix at least one contact element, a base section, and an arm extending from the base section substantially along the connection direction, wherein the arm includes at least one securing element for securing the connector against the connection direction, and wherein the base section is located closer to a distal end of the connector than the contact section, the distal end being opposite to the proximal end along the connection direction. A connection assembly includes the connector and a mating connector. A connection group includes the connection assembly and a bulkhead that receives the connection assembly.

Abstract: A clamping triaxial seepage and acoustic coupling rock tensile testing machine includes a sample and a scaffold-type tensile testing device. The scaffold-type tensile testing device has an upper chuck and a lower chuck. The upper chuck has an acoustic transmitting channel, one end of which communicating with the outside, and the other end of which having an acoustic transmitting probe. The lower chuck has an acoustic receiving channel, one end of which communicating with the outside, and the other end having acoustic receiving probe. An upper end face of the sample has with a seepage outflow hole while the upper chuck has a seepage outflow channel connected with the seepage outflow hole. A lower end face of the sample has a seepage inflow hole while the lower chuck has a seepage entry channel is connected with the seepage inflow hole.

Abstract: A neural network training method includes performing, in a forward propagation process, binarization processing on a target weight by using a binarization function, and using data obtained through the binarization processing as a weight of a first neural network layer in a neural network; and calculating, in a backward propagation process, a gradient of a loss function with respect to the target weight by using a gradient of a fitting function as a gradient of the binarization function.

Abstract: Embodiments of this disclosure relate to the field of artificial intelligence, and disclose a feature extraction method and apparatus. The method includes: obtaining a to-be-processed object, and obtaining a segmented object based on the to-be-processed object, where the segmented object includes some elements in the to-be-processed object, a first vector indicates the segmented object, and a second vector indicates some elements in the segmented object; performing feature extraction on the first vector to obtain a first feature, and performing feature extraction on the second vector to obtain a second feature; fusing at least two second features based on a first target weight, to obtain a first fused feature; and performing fusion processing on the first feature and the first fused feature to obtain a second fused feature, where the second fused feature is used to obtain a feature of the to-be-processed object.

Abstract: Embodiments of this application disclose a convolutional neural network pruning processing method, a data processing method, and a device, which may be applied to the field of artificial intelligence. The convolutional neural network pruning processing method includes: performing sparse training on a convolutional neural network by using a constructed objective loss function, where the objective loss function may include three sub-loss functions.

Abstract: An image processing method is disclosed in embodiments of this disclosure and is applied to the field of artificial intelligence. The method includes: obtaining an input feature map of an image to be processed, where the input feature map includes a first input sub-feature map and a second input sub-feature map, and resolution of the first input sub-feature map is higher than resolution of the second input sub-feature map; performing feature fusion processing on the input feature map by using a target network, to obtain an output feature map, where a feature of the first input sub-feature map is fused to a feature of the second input sub-feature map from a low level to a high level in the target network; and performing, based on the output feature map, object detection on the image to be processed, to obtain an object detection result.

Abstract: This disclosure discloses a perception network. The perception network may be applied to the artificial intelligence field, and includes a feature extraction network. A first block in the feature extraction network is configured to perform convolution processing on input data, to obtain M target feature maps; at least one second block in the feature extraction network is configured to perform convolution processing on M1 target feature maps in the M target feature maps, to obtain M1 first feature maps; a target operation in the feature extraction network is used to process M2 target feature maps in the M target feature maps, to obtain M2 second feature maps; and a concatenation operation in the feature extraction network is used to concatenate the M1 first feature maps and the M2 second feature maps, to obtain a concatenated feature map.

Abstract: A method is provided for data processing based on a multi-layer perceptrons (MLP) architecture. The method comprises determining a plurality of tokens for a piece of data, generating an amplitude and a phase for each of the plurality of tokens, optimizing the plurality of tokens by mixing the plurality of tokens based on the amplitudes and the phases, and determining one or more features included in the piece of data based on the plurality of optimized tokens. Each token includes information associated with a segment of the piece of data.

Abstract: Embodiments of this application disclose a model structure, a method for training a model, an image enhancement method, and a device, and may be applied to the computer vision field in the artificial intelligence field. The model structure includes: a selection module, a plurality of first neural network layers, a segmentation module, a transformer module, a recombination module, and a plurality of second neural network layers. The model overcomes a limitation that the transformer module can only be used to process a natural language task, and may be applied to a low-level vision task. The model includes the plurality of first/second neural network layers, and different first/second neural network layers correspond to different image enhancement tasks. Therefore, after being trained, the model can be used to process different image enhancement tasks.

Abstract: A neural network training method, includes: obtaining an input feature map of a training image; performing feature extraction processing on the input feature map by using a feature extraction core of a neural network to obtain a first candidate feature map; adding the first candidate feature map and a second candidate feature map to obtain an output feature map, where the second candidate feature map is a feature map obtained after a value corresponding to each element in the input feature map is increased by N times, and N is greater than 0; determining an image processing result of the training image based on the output feature map; and adjusting a parameter of the neural network based on the image processing result.

Abstract: The technology of this application relates to a neural network distillation method, applied to the field of artificial intelligence, and includes processing to-be-processed data by using a first neural network and a second neural network to obtain a first target output and a second target output, where the first target output is obtained by performing kernel function-based transformation on an output of the first neural network layer, and the second target output is obtained by performing kernel function-based transformation on an output of the second neural network layer. The method further includes performing knowledge distillation on the first neural network based on a target loss constructed by using the first target output and the second target output.

Abstract: A data feature extraction method and apparatus in the field of artificial intelligence are provided. An addition convolution operation is performed to extract a target feature in quantized data based on quantized feature extraction parameters, that is, to calculate a sum of absolute values of differences between the quantized feature extraction parameters and the quantized data, to obtain the target feature based on the sum. In addition, feature extraction parameters and data are quantized by using a same quantization parameter. According to this application, a storage resource is saved, a computing resource is saved, thereby reducing a limitation on an application of artificial intelligence to a resource-limited device. Further, when the extracted feature data is dequantized, the feature data may be dequantized based on the quantization parameters.

Abstract: A neural network training method in the artificial intelligence field includes: inputting training data into a neural network; determining a first input space of a second target layer in the neural network based on a first output space of a first target layer in the neural network; and inputting a feature vector in the first input space into the second target layer, where a capability of fitting random noise by the neural network when the feature vector in the first input space is input into the second target layer is lower than a capability of fitting the random noise by using an output space that is in the neural network and that exists when a feature vector in the first output space is input into the second target layer. This application helps avoid an overfitting phenomenon that occurs when the neural network processes an image, text, or speech.

Abstract: An electrical connector includes a conductive housing having a first receiving portion with an open end, a movable terminal having a first end inserted into the first receiving portion via the open end, the movable terminal having a second receiving portion, and a first elastic piece located in a space defined by the first receiving portion and the second receiving portion. A second end of the movable terminal opposite to the first end protrudes movably out of the first receiving portion against an elasticity of the first elastic piece. The first end of the movable terminal has a first elastic arm elastically abutting an inner side wall of the first receiving portion. The movable terminal is electrically connected to the conductive housing by each of the first elastic piece and the first elastic arm.

Abstract: This application provides a neural network model compression method in the field of artificial intelligence. The method includes: obtaining, by a server, a first neural network model and training data of the first neural network that are uploaded by user equipment; obtaining a PU classifier based on the training data of the first neural network and unlabeled data stored in the server; selecting, by using the PU classifier, extended data from the unlabeled data stored in the server, where the extended data has a property and distribution similar to a property and distribution of the training data of the first neural network model; and training a second neural network model by using a knowledge distillation (KD) method based on the extended data, where the first neural network model is used as a teacher network model and the second neural network model is used as a student network model.

Abstract: An electrical connector includes an electrical connector housing having a body with a receiving portion, a movable pin, a part of the movable pin is movably disposed in the receiving portion, a first elastic piece disposed in the receiving portion, and a second elastic piece located between a side wall of the receiving portion and the movable pin and elastically abutted against an outer circumferential surface of the movable pin. A first end of the movable pin movably protrudes out of the receiving portion against an elasticity of the first elastic piece. The movable pin is electrically connected to the electrical connector housing by the first elastic piece and the second elastic piece.

Abstract: This application relates to an image recognition technology in the field of computer vision in the field of artificial intelligence, and provides an image classification method and apparatus. The method includes: obtaining an input feature map of a to-be-processed image; performing convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain a candidate output feature map of M channels, where M is a positive integer; performing matrix transformation on the M channels of the candidate output feature map based on N matrices, to obtain an output feature map of N channels, where a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and classify the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.

Abstract: This application relates to an image recognition technology in the field of computer vision of artificial intelligence, and provides an image classification method and apparatus. The method includes: obtaining an input feature map of a to-be-processed image; performing feature extraction processing on the input feature map based on a feature extraction kernel of a neural network, to obtain an output feature map, where each of a plurality of output sub-feature maps is determined based on the corresponding input sub-feature map and the feature extraction kernel, at least one of the output sub-feature maps is determined based on a target matrix obtained after an absolute value is taken, and a difference between the target matrix and the input sub-feature map corresponding to the target matrix is the feature extraction kernel; and classifying the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.

Abstract: A connector includes a pair of outer conductors including a first outer conductor and a second outer conductor assembled together and slidable with respect to each other, a pair of center conductors arranged within the outer conductors, an insulation seat, and an elastic element. The center conductors include a first center conductor and a second center conductor assembled together and slidable with respect to each other. The first outer conductor and the first center conductor are fixed to the insulation seat. A first end of the elastic element abuts against the first outer conductor or the insulation seat. The first outer conductor and the first center conductor are both in electrical contact with a first electrical component under a pressing force from the elastic element.

Abstract: The present application discloses an image generation method, a neural network compression method, and a related apparatus and device in the field of artificial intelligence. The image generation method includes: inputting a first matrix into an initial image generator to obtain a generated image; inputting the generated image into a preset discriminator to obtain a determining result, where the preset discriminator is obtained through training based on a real image and a category corresponding to the real image; updating the initial image generator based on the determining result to obtain a target image generator; and further inputting a second matrix into the target image generator to obtain a sample image. Further, a neural network compression method is disclosed, to compress the preset discriminator based on the sample image obtained by using the foregoing image generation method.