Methods, systems, and apparatus, including computer programs encoded on computer storage media, for real-time deployment of machine learning networks. One of the operations is performed by the system receiving video data from a video image capturing device. The received video data is converted into multiple video frames. These video frames are encoded into a particular color space format. The system renders a first display output depicting imagery from the multiple encoded video frames. The system performs an inference on the video frames using a machine learning network in order to determine the occurrence of one or more objects in the video frames. The system renders a second display output depicting graphical information corresponding to the determined one or more objects from the multiple encoded video frames. The system then generates a composite display output including the imagery of the first display output overlaid with the graphical information of the second display output.

Systems and methods for tailoring a single prescription for different users for completing tasks on equipment are provided. A prescription representative of a flowchart or decision tree for performing a main set of the tasks is obtained. Characteristics of the equipment and/or a user of the prescription are obtained. Content of the prescription that is displayed to the user during performance of at least some of the tasks on the equipment is tailored based on the characteristics. The content of the prescription is tailored by hiding one or more of the tasks that are not applicable to the equipment from display to the user. This can occur without any data or information being removed from or added to the prescription. Instead, the prescription can be tailored by changing what information is automatically and/or initially displayed to the user.

In some embodiments, a processor can receive an input string associated with a potentially malicious artifact and convert each character in the input string into a vector of values to define a character matrix. The processor can apply a convolution matrix to a first window of the character matrix to define a first subscore, apply the convolution matrix to a second window of the character matrix to define a second subscore and combine the first subscore and the second subscore to define a score for the convolution matrix. The processor can provide the score for the convolution matrix as an input to a machine learning threat model, identify the potentially malicious artifact as malicious based on an output of the machine learning threat model, and perform a remedial action on the potentially malicious artifact based on identifying the potentially malicious artifact as malicious.

A method for cleaning up a background application, a storage medium, and an electronic device are provided. The method includes the following. Collect multi-dimensional feature information associated with an application as samples to construct a sample set associated with the application. Extract feature information from the sample set to construct multiple training sets. Train each training set to generate a corresponding decision tree. Predict, with multiple decision trees generated, current feature information associated with the application and output multiple predicted results when the application is switched to the background, where the predicted results include predicted results indicative of that the application is able to be cleaned up and predicted results indicative of that the application is unable to be cleaned up. Determine whether the application is able to be cleaned up according to the multiple predicted results. Clean up the application when the application can be cleaned up.

The present teaching relates to generating an updated model related to advertisement selection. In one example, a request is obtained for updating a model to be utilized for selecting an advertisement. A plurality of copies of the model is generated. The model is pre-selected based on a performance metric related to advertisement selection. Based on each of the plurality of copies, a candidate model is created by modifying one or more parameters of the copy of the model to create a plurality of candidate models. One of the plurality of candidate models is selected based on the performance metric. The steps of generating, creating, and selecting are repeated until a predetermined condition is met. The model is updated with the latest selected candidate model when the predetermined condition is met.

Data drift or dataset shift is detected between training dataset and test dataset by training a scoring function using a pooled dataset, the pooled dataset including a union of the training dataset and the test dataset; obtaining an outlier score for each instance in the training dataset and the test dataset based at least in part on the scoring function; assigning a weight to each outlier score based at least in part on training contamination rates; determining a test statistic based at least in part on the outlier scores and the weights; determining a null distribution of no dataset shift for the test statistic; determining a threshold in the null distribution; and when the test statistic is greater than or equal to the threshold, identifying dataset shift between the training dataset and the test dataset.

An automatic supplier recommendation engine for suggesting a product supplier from outside of an existing merchant network is disclosed. A set of optimization solutions may include pricing, performance, shipping, duties, trust score and other inventory or manufacturing factors. The set of optimization solutions are run on a processor to determine optimal fulfillment for products in an e-commerce platform. A set of heuristics may include geographic location, quality, sizing of purchases, similarity of supplier offerings, supplier positioning and other attributes may be created for merchants and suppliers. The set of optimization solutions are run, and the set of heuristics for each merchant and for each supplier are compared, to determine whether a match exists. A prospective merchant-supplier relationship may be communicated and established via an e-commerce platform.

The present disclosure relates to a computer-implemented method for electronic design. Embodiments may include receiving, using at least one processor, an electronic design schematic and optionally an electronic design layout. Embodiments may further include analyzing the electronic design schematic to determine if one or more required features of a particular circuit structure are present. If the one or more required features are present, embodiments may include analyzing, using a machine learning model, the electronic design schematic to determine if one or more optional features of the particular circuit structure are present.

A heuristic engine includes capabilities to collect an unstructured data set and a current business context to calculate a credit worthiness score. Providing a heuristic algorithm, executing within the engine, with the data set and the context may allow determination of predicted future contexts and recommend subsequent actions, such as assessing a credit risk of a customer transaction and reducing the risk of customer transactions by processing the available data. Such heuristic algorithms may learn from past data transactions and appropriate correlations with events and available data.

A method for modeling loan transitions may include defining a plurality of potential repayment states of an individual loan between origination and a terminal state comprising either a paid off state or a charged off state, where the potential repayment states include a current state, a plurality of delinquency states distinguished from each other based on length of delinquency, the paid off state and the charged off state. The method may further include defining valid transitions between a present state among the potential repayment states and each respective one of the potential repayment states that is a possible next state from the present state, and determining, for the individual loan, a probability of transitioning from the present state to the next state during each period of a term of the individual loan.