Abstract: Described are techniques for machine learning library management. The techniques include generating a table including a plurality of machine learning libraries and their current versions that are used in a deployed machine learning platform (MLP) instance, a first available version upgrade for a first machine learning library of the plurality of machine learning libraries, a security indication associated with the first available version upgrade relative to a current version implemented by the first machine learning library, and a compatibility indication between the first available version upgrade and the current version of the first machine learning library. The techniques further include generating a recommendation related to upgrading the first machine learning library based on the security indication and the compatibility indication.

Abstract: Provided are a computer-implemented method, a system, and a computer program product. The method comprises extracting features from a plurality of base models in an ensemble model. The plurality of base models are configured to provide respective prediction results. The ensemble model is configured to provide an overall prediction result from the prediction results of the plurality of base models. The features are associated with time performance of the base models. The method further comprises clustering the plurality of base models into a plurality of clusters based on the extracted features. The method further comprises assigning the plurality of base models to a plurality of parallel computation units based on the plurality of clusters.

Abstract: A computer-implemented system, platform, programing product, and/or method for improving transformation selection in an ensemble machine learning (ML) model that includes: providing all base ML models of the ensemble ML model; identifying all of a plurality of Derived Fields in all the base ML models; performing a Derived Field run prediction analysis for all the Derived Fields; computing the Derived Field Importance Weight for Field (DFIW4F) and the Derived Field Importance Weight for Model (DFIW4M) for all the Derived Fields; clustering all the Derived Fields into a plurality of Derived Field clusters, wherein each Derived Field cluster is based upon the DFIW4M and the DFIW4F for the Derived Field; sorting all the Derived Field clusters by best cluster based upon DFIW4M and DFIW4F; and running the base ML models based upon the Derived Fields in the best Derived Field cluster until sufficient base ML models have been run.

Abstract: A trolley configured for use to carry folding tables of a variety of sizes. The trolley includes a loading end, a trolley frame, and an extension gate adjustably connected to the trolley frame so as to be adjustable relative to the loading end of the trolley in a length direction of the trolley. The extension gate includes an elongate member slidingly disposed on the trolley frame and a rotatable portion that is foldable relative to the elongate member and lockable in an upright position by a lock. The rotatable portion may be positioned in an extended position from the loading end of the trolley, in a retracted position adjacent the loading end of the trolley, and in positions that are intermediate to the extended position and the retracted position. The elongate member may slide in a first direction to extend the rotatable portion away from the loading end of the trolley and in a second direction to retract the rotatable portion toward the loading end of the trolley.

Abstract: Constructing a feature segment-based ensemble can include generating a data structure for each element of an initial set of training data. Multiple strongly correlated features of the elements can be identified as well as weakly correlated features. For each strongly correlated feature, a feature segmentation training set can be generated, each training set's elements each containing one of the strongly correlated features and excluding other strongly correlated features. One or more machine learning algorithms can be selected from a software library. The one or more machine learning algorithms can be applied to the feature segmentation training sets to train multiple machine learning models. Each machine learning model that improves the predictive accuracy of the feature segment-based ensemble can be integrated in the feature segment-based ensemble.

Abstract: A processing method applied to a first electronic device, the method including obtaining first audio data and/or first image data; performing at least one process on the first audio data and/or the first image data to obtain target data to be outputted; and outputting the target data to be outputted to a target application running on a second electronic device having a communication connection with the first electronic device. The target application is configured to directly output the target data to be outputted. The data size of the target data to be outputted is different from data size of the first audio data and/or the first image data.

Abstract: In an approach for detecting web browsing subject-oriented event interactions and intelligently organizing web pages based on insights from important interactions for better exploration and efficient management, a processor extracts time series data associated with a plurality of web browsing events based on browsing historical actions of a user. A processor identifies the subject of each web browsing event. A processor determines major events based on the time series data and subjects of the plurality of web browsing events. A processor organizes the plurality of web browsing events based on subject hierarchy and timeline from the time series data. A processor highlights one or more uniform resource locators based on the subject hierarchy and timeline.

Abstract: Provided are an information recommendation method and apparatus. According to historical data, an information recommendation apparatus identifies a pair of matching items so as to determine a cross-category relationship of items; the item cross-category relationship is used to construct item match contexts; an item context portrait and a user context portrait are used to sort the match contexts; the items in the match contexts are sorted according to the feedback behavior of the user concerning the items in the match contexts; the sorted match contexts are recommended to the user.

Abstract: A head-up display includes a picture generation unit and a first lens. The picture generation unit is configured to output a first light ray and a second light ray. The first light ray is used to output and display a first picture, and the second light ray is used to output and display a second picture. When the first lens is at the first position, the first light ray and the second light ray do not pass through the first lens. When the first lens is at the second position, the first light ray passes through the first lens. The head-up display can implement switching between a single image plane and a plurality of image planes.

Abstract: Techniques for optimizing machine learning models are provided. A first model in a first format is received. A second model is generated by applying one or more optimization techniques to the first model; the second model is an optimized version of the first model. The second model is converted into a common intermediate format. The second model is converted into binary data representing the second model. The binary data representing the second model is outputted.

Abstract: A mixer for generating particles, comprising a first mixing unit, wherein the first mixing unit comprises a first channel (702) and a second channel (701), the first channel (702) comprises a rectilinear channel, the second channel (701) comprises a curvilinear channel. The mixer is particularly suitable for producing nanoparticles, and the mixing efficiency can be improved. A microfluidic hybrid chip cartridge prepared by the mixer is also provided.

Abstract: A computer implemented method for managing datasets for a histogram. The method uses a number of processor units to determine a first span for first bins containing first datapoints in a first dataset in the datasets. The first span is determined based a distribution of the first datapoints in the first dataset and a desired number of bins. The number of processor units adjusts a second span for second bins containing second datapoints in a second dataset in the datasets to form an adjusted span that matches the first span for the first bins. The number of processor units merges the first datapoints in the first bins having the first span with the second datapoints in the second bins having the adjusted span to form a merged dataset for the histogram.

Abstract: Embodiments of the present disclosure relate to methods, systems, and computer program products for optimized prediction of a tree ensemble. According to a method, an input request is received, which indicates a plurality of input values for a plurality of variables associated with a tree ensemble. A plurality of target transformed intervals, into which the plurality of input values fall respectively, are determined by matching the plurality of input values with a plurality of sets of transformed intervals for the plurality of variables respectively. Respective prediction results for a plurality of tree models of the tree ensemble are determined based on the plurality of target transformed intervals and respective node hierarchies of the plurality of tree models. A tree ensemble prediction result is determined for the input request based on the determined prediction results of the plurality of tree models.

Abstract: One or more computer processors calculate a cache prediction for a received inference request within an inference cache structured as a self-learning tree, wherein the inference request comprises a set of input values. The one or more computer processors responsive to the retrieved cache prediction exceeding a cache prediction threshold, transmit the cache prediction. The one or more computer processors parallel compute a model prediction for the received inference request utilizing a trained model. The one or more computer processors responsive to the retrieved model prediction exceeding a model prediction threshold, convert the trained model into a tree structure. The one or more computer processors update the inference cache with the converted train model. The one or more computer processors transmit the model prediction.

Abstract: In an approach for detecting web browsing subject-oriented event interactions and intelligently organizing web pages based on insights from important interactions for better exploration and efficient management, a processor extracts time series data associated with a plurality of web browsing events based on browsing historical actions of a user. A processor identifies the subject of each web browsing event. A processor determines major events based on the time series data and subjects of the plurality of web browsing events. A processor organizes the plurality of web browsing events based on subject hierarchy and timeline from the time series data. A processor highlights one or more uniform resource locators based on the subject hierarchy and timeline.

Abstract: The present disclosure provides a display panel including a display layer and an antenna layer. The display layer includes pixel units arranged according to a first rule. The antenna layer is arranged on a light-exiting side of the display layer and includes multiple metal grid units that are uniformly arranged in the antenna layer according to a second rule. The antenna layer includes a first area and a second area. The metal grid units in the first area are in conduction with each other and are not in conduction to the metal grid units in other areas to form an antenna unit. The second area is a non-antenna area. The ratio of the total area of the first area and the second area to the area of the display layer is greater than 90%.

Abstract: A method includes determining a plurality of performance metrics for a plurality of sub-models forming a first machine learning model and clustering the plurality of sub-models based on the plurality of performance metrics to produce a plurality of clusters of sub-models. The method also includes removing, from the first machine learning model, sub-models assigned to a first cluster of the plurality of clusters to produce a second machine learning model formed by the sub-models remaining in the first machine learning model and in response to determining that a performance of the second machine learning model is below a performance threshold, adding a subset of the removed sub-models to the second machine learning model to produce a third machine learning model. The method further includes, in response to determining that a performance of the third machine learning model meets the performance threshold, selecting the third machine learning model to be applied.

Abstract: ?1-2-fucosyltransferases, and methods and compositions for making and using ?1-2-fucosyltransferases, are described herein.

Abstract: Systems and computer-implemented methods select a subset of methods to generate data schemas for input data from a list of methods for generating data schemas, based on output of a regression model; generate a candidate schema for each method in the subset of methods to generate data schemas; and generate a master data schema for the input data by merging the candidate schema for each method in the subset of methods to generate data schemas, utilizing predetermined rules.

Abstract: A computer-implemented method, system and computer program product for detecting feature traits from an imbalanced dataset. A first regression model is built based on a simulated dataset to compute contribution scores for the features to make a target a positive case. A variance in the features' original values for each feature of the first set of features (those features with contribution scores for positive cases that exceed a threshold value) between the positive and negative cases is determined. A second regression model is built to calculate a predictor importance value for a second set of features (features from the first set of features with a variance in their original values for both positive and negative cases that exceeds a threshold value). Feature traits are then extracted from a group of clustered positive cases with features of the second set of features containing a predictor importance value exceeding a threshold value.