Abstract: A purified oligosaccharide compound having antithrombotic activity or a mixture of a homologous compound thereof and a pharmaceutically acceptable salt thereof, a preparation method for the mixture, a pharmaceutical composition containing the mixture, and uses thereof serving as an intrinsic factor X-enzyme (Xase) inhibitor in the preparation of drugs for preventing and/or treating thrombotic diseases.

Abstract: This application relates to a model migration method in the field of artificial intelligence, including: obtaining sample data of a target task, where the sample data includes a plurality of image samples; separately evaluating N pre-trained models based on the sample data, to obtain N evaluation values, where the evaluation value represents adaptation between the pre-trained model and the target task, and N?2; determining K pre-trained models from the N pre-trained models based on the N evaluation values, where the K pre-trained models are models corresponding to first K evaluation values obtained by sorting the N evaluation values in descending order, and 1?K?N; and processing the sample data based on the K pre-trained models to obtain a target model used to process the target task, where the target model includes the K pre-trained models.

Abstract: An detachment device for a spliced display device includes: a detachment mechanism disposed to be connected with the first display unit to drive the first display unit to move along a direction away from or close to a plane where the spliced display device is located; at least one moving device, wherein the moving device includes a moving frame located outside the detachment mechanism and an adjustment member disposed on the moving frame, the moving frame is connected with the second display unit, the adjustment member abuts against the detachment mechanism, and the moving frame drives the second display unit connected with the moving frame to move in a direction away from the first display unit through the adjustment member on the plane where the spliced display device is located.

Abstract: An intelligent modeling method of a Selective Catalytic Reduction (SCR) reaction process of diesel vehicle exhaust includes the following steps: S1: acquiring a time sequence data set of an SCR reaction process of diesel vehicle exhaust for modeling, where the time sequence data set includes an input variable sequence and an output variable sequence; S2: selecting a multi-layer type-II fuzzy neural network as an SCR reaction process model of diesel vehicle exhaust based on the input variable sequence and the output variable sequence obtained in Si. The intelligent modeling method of the SCR reaction process of diesel vehicle exhaust can effectively model dynamic characteristics of the SCR reaction process such as nonlinearity, time delay and uncertain interference, and improve the accuracy, robustness and generalization ability of the SCR reaction process model.

Abstract: This disclosure discloses lane line detection methods and devices. In an implementation, features extracted by different layers of the neural network are fused to obtain a fused second feature map, so that the second feature map obtained through fusion processing has a plurality of layers of features. The fused second feature map has a related feature of a low-layer receptive field and a related feature of a high-layer receptive field. Afterwards, an output predicted lane line set is divided into groups, where each predicted lane line in each group has an optimal prediction interval.

Abstract: A processing entity generates a model for estimating scene illumination colour for a source image captured by a camera The processing entity acquires a set of images, captured by a respective camera, the set of images as a whole including images captured by multiple cameras; forms a set of tasks by assigning each image of the images set to a respective task such that images in the same task have in common that a the images are in a predetermined range; trains model parameters by repeatedly: selecting at least one of the tasks, forming an interim set of model parameters based on a first subset of the images of that task, estimating the quality of the interim set of model parameters against a second subset of the images of that task and updating the parameters of the model based on the interim set of parameters and the estimated quality.

Abstract: Disclosed is a method for searching for a neural network architecture ensemble model. The method includes: obtaining a dataset, where the dataset includes a sample and an annotation in a classification task; performing search by using a distributional neural network architecture search algorithm, including: determining a hyperparameter of a neural network architecture distribution; sampling a valid neural network architecture from the architecture distribution defined by the hyperparameter; training and evaluating the neural network architecture on the dataset, to obtain a performance indicator; determining, based on the performance indicator, neural network architecture distributions that share the hyperparameter, to obtain a candidate pool of base learners; and determining a surrogate model; and predicting test performance of the base learner in the candidate pool by using the surrogate model, and determining that k diverse base learners that meet a task scenario requirement form an ensemble model.

Abstract: Embodiments of the present invention provide a machine learning model training method, including: obtaining target task training data and N categories of support task training data; inputting the target task training data and the N categories of support task training data into a memory model to obtain target task training feature data and N categories of support task training feature data; training the target task model based on the target task training feature data and obtaining a first loss of the target task model, and separately training respectively corresponding support task models based on the N categories of support task training feature data and obtaining respective second losses of the N support task models; and updating the memory model, the target task model, and the N support task models based on the first loss and the respective second losses of the N support task models.

Abstract: An image classification method and apparatus, and an image classification model training method and apparatus are provided, which are related to an image recognition technology in the artificial intelligence field and more specifically, to the computer vision field. The method includes: obtaining a to-be-processed image; and classifying the to-be-processed image based on a preset global class feature, to obtain a classification result of the to-be-processed image. The preset global class feature includes a plurality of class features obtained through training based on a plurality of training images in a training set. The plurality of class features in the preset global class feature are used to indicate visual features of all classes in the training set.

Abstract: This application relates to the field of artificial intelligence, and discloses a data encoding method, a data decoding method, and data processing apparatuses. Both the data encoding method and the data decoding method relate to an invertible flow-based model. The invertible flow-based model includes a target invertible flow layer, a model parameter of the target invertible flow layer is used to constrain an auxiliary variable generated in an inverse transform processing process, an operation corresponding to the target invertible flow layer includes a multiplication operation and a division operation that are determined based on the model parameter, and the auxiliary variable is an increment of a product of the multiplication operation or a remainder generated through the division operation.

Abstract: A neural network obtaining method, a data processing method, and a related device are disclosed. The disclosed methods may be used in the field of automatic neural architecture search technologies in the field of artificial intelligence. An example method includes: obtaining first indication information, where the first indication information indicates a probability and/or a quantity of times that k neural network modules appear in a first neural architecture cell; generating the first neural architecture cell based on the first indication information, and generating a first neural network; obtaining a target score corresponding to the first indication information, where the target score indicates performance of the first neural network; and obtaining second indication information from a plurality of pieces of first indication information based on a plurality of target scores, and obtaining a target neural network corresponding to the second indication information.

Abstract: An image classification method includes obtaining a first feature of a reference image and a second feature of a to-be-classified image; generating a third feature based on the first feature and the second feature; generating a first classification result based on the first feature, where the first classification result is used to determine a category of the reference image; generating a second classification result based on the third feature; and generating a third classification result based on the first classification result and the second classification result, where the third classification result is used to determine a category of the to-be-classified image.

Abstract: The present disclosure provides molecular sieves with intergrown phases of AEI and CHA topologies and a catalyst thereof. A preparation method for the molecular sieves include the following steps: mixing a hydroxyphosphono organic alkali R with an aluminum source and a silicon source to obtain a sol-gel precursor, putting the sol-gel precursor into a closed hydrothermal synthesis reactor for reaction, filtering the reaction solution, washing, drying, and calcination to obtain the molecular sieves with intergrown phases of AEI and CHA topologies. The molecular sieves and the catalyst thereof can be directly synthesized under mild conditions with a hydroxyphosphono organic alkali as a structure-directing agent and a phosphorus source, have a pH value of 6-9 and low requirements for corrosion resistance of production devices, and are suitable for large-scale production.

Abstract: The present disclosure provides msect-4 molecular sieves with OFF and ERI topologies, a preparation method therefor, and applications thereof. An eight-membered ring small pore molecular sieve used as a raw material is dispersed in an aqueous phase. Following that, caustic potash, an aluminum source, and an organic structure-directing agent (OSDA) are added. The pH value is then adjusted to be greater than 10, and a silicon source is introduced to attain the desired silicon-aluminum ratio, followed by stirring reaction, aging, crystallization, filtration, washing, ammonia exchange reaction, drying, and calcination. The msect-4 molecular sieves with OFF and ERI topologies, the preparation method therefor, and applications exhibit excellent hydrothermal stability, a plurality of adsorption sites exposed by a regular bone-like structure, and a large specific surface area.

Abstract: This application relates to the artificial intelligence field, and discloses a neural network search method and a related apparatus. The neural network search method includes: constructing attention heads in transformer layers by sampling a plurality of candidate operators during model search, to construct a plurality of candidate neural networks, and comparing performance of the plurality of candidate neural networks to select a target neural network with higher performance. In this application, a transformer model is constructed with reference to model search, so that a new attention structure with better performance than an original self-attention mechanism can be generated, and effect in a wide range of downstream tasks is significantly improved.

Abstract: A method, an apparatus, and a system for generating a neural network model, a device, a medium, and a program product are provided. In an embodiment, a first device sends an indication about a structure of a subnetwork model to a second device, where the subnetwork model is determined by adjusting a structure of a hypernetwork model. The first device receives a parameter of the subnetwork model from the second device, where the parameter of the subnetwork model is determined by the second device based on the indication and the hypernetwork model. The first device trains the subnetwork model based on the received parameter of the subnetwork model. The first device sends a parameter of the trained subnetwork model to the second device for the second device to update the hypernetwork model. In the foregoing manner, an efficient federated learning scheme between a plurality of devices is provided.

Abstract: A method is provided for data processing performed by a processing system. The method comprises determining a set of first tokens for first data and a set of second token for second data, each token comprising information associated with a segment of the respective data, determining pair-wise similarities between the set of first tokens and the set of second tokens, each pair comprising a first token in the set of first tokens and a second token in the set of second tokens, determining, for each first token in the set of first tokens, a maximum similarity based on the determined pair-wise similarities between the respective first token and the second tokens in the set of second tokens, and determining a first similarity between the first data and the second data by aggregating the maximum similarities corresponding to the first tokens in the set of first set of tokens.

Abstract: A purified oligosaccharide compound having antithrombotic activity or a mixture of a homologous compound thereof and a pharmaceutically acceptable salt thereof, a preparation method for the mixture, a pharmaceutical composition containing the mixture, and uses thereof serving as an intrinsic factor X-enzyme (Xase) inhibitor in the preparation of drugs for preventing and/or treating thrombotic diseases.

Abstract: A data encoding method includes obtaining to-be-encoded data; processing the to-be-encoded data by using a volume preserving flow model to obtain a hidden variable output, where the volume preserving flow model includes a target volume preserving flow layer, an operation corresponding to the target volume preserving flow layer is an invertible operation that meets a volume preserving flow constraint, the target volume preserving flow layer is used to perform a multiplication operation on a preset coefficient and first data input to the target volume preserving flow layer, and the preset coefficient is not 1; and encoding the hidden variable output to obtain encoded data.

Abstract: A purified oligosaccharide compound having antithrombotic activity or a mixture of a homologous compound thereof and a pharmaceutically acceptable salt thereof, a preparation method for the mixture, a pharmaceutical composition containing the mixture, and uses thereof serving as an intrinsic factor X-enzyme (Xase) inhibitor in the preparation of drugs for preventing and/or treating thrombotic diseases.