Abstract: Certain aspects of the present disclosure provide techniques for performing finite rank deep kernel learning. In one example, a method for performing finite rank deep kernel learning includes receiving a training dataset; forming a set of embeddings by subjecting the training dataset to a deep neural network; forming, from the set of embeddings, a plurality of dot kernels; linearly combining the plurality of dot kernels to form a composite kernel for a Gaussian process; receiving live data from an application; and predicting a plurality of values and a plurality of uncertainties associated with the plurality of values simultaneously using the composite kernel.

Abstract: A method including transforming metrics, related to a computer network environment, into a digital image including pixels that represent the metrics. The computer network environment initially is load balanced by a first load balancing scheme selected from among load balancing schemes. The method also includes generating a classification of the digital image. The method also includes selecting, based on the classification of the digital image, a selected load balancing scheme from among the load balancing schemes. The method also includes changing the first load balancing scheme to the selected load balancing scheme such that the selected load balancing scheme is applied to the computer network environment.

Abstract: A computing system generates a plurality of training data sets for generating the NLP model. The computing system trains a teacher network to extract and classify tokens from a document. The training includes a pre-training stage where the teacher network is trained to classify generic data in the plurality of training data sets and a fine-tuning stage where the teacher network is trained to classify targeted data in the plurality of training data sets. The computing system trains a student network to extract and classify tokens from a document by distilling knowledge learned by the teacher network during the fine-tuning stage from the teacher network to the student network. The computing system outputs the NLP model based on the training. The computing system causes the NLP model to be deployed in a remote computing environment.

Abstract: Certain aspects of the present disclosure provide techniques for configuring a software application through a remote configuration service. An example method generally includes receiving, from a remote configuration service, a declarative construct. Generally, the declarative construct includes a definition of a workflow in an application to be executed within a player application deployed on a client device. Information associated with the definition of the workflow is extracted by parsing the declarative construct according to a schema defining a format of the declarative construct. The workflow is executed in the player application based on the extracted information defining functionality of the workflow.

Abstract: Systems and methods for training machine learning models are disclosed. An example method includes receiving a semi-labeled set of training samples including a first set of training samples, where each training sample in the first set is assigned a known label, and a second set of training samples, where each training sample in the second set has an unknown label, determining a first loss component, the first loss component providing a loss associated with the first set, determining a second loss component, the second loss component having a value which increases based on a difference between a distribution of individually predicted values of at least the second set and an expected overall distribution of at least the second set, and training the machine learning model, based on the first loss component and the second loss component, to predict labels for unlabeled input data.

Abstract: A two-stage machine learning model is used to for categorization of a dataset, such as transactions. A plurality of complementary base machine learning models are used to generate initial inference results and associated measures of inference confidence from the dataset, which are collected as a meta dataset. Each of the complementary models is associated with a different part of the dataset in which it has a higher accuracy in that part than the other models. The meta dataset is provided as input to a meta machine learning model, which is trained to produce a final inference result, and a confidence score model, which is trained to produce a confidence score associated with the final inference result.

Abstract: A method implements input validation using mathematical expressions. The method includes receiving an input string, scanning the input string to locate a hit string matching a hit expression from a validation package, and converting the hit string to a list of values corresponding to characters from the hit string. The method further includes validating the hit string by evaluating a validation expression from the validation package using the list of values to generate a validation result and returning the validation result.

Abstract: A method implements efficient counterfactual search. The method includes receiving a request corresponding to an input vector, processing the input vector with a model to generate an output vector that does not correspond to a selected class, and processing the input vector using a component, of a plurality of components, to generate a counterfactual vector to the selected class. The plurality of components includes a number of dimensions that is less than a number of features of the input vector. The method further includes processing the counterfactual vector to generate a recommendation and presenting the recommendation.

Abstract: Certain aspects of the present disclosure provide techniques for processing computing resource access requests from users of an application service. An example method generally includes measuring computing resource access metrics over a time window for a user of a computing system. The measured computing access metrics for the user of the computing system are determined to exceed a threshold. Based on determining that the measured computing access metrics for the user of the computing system exceeds the threshold, computing resource access requests from the user of the computing system are migrated from a first queue to a second queue, wherein the first queue comprises a rate-unlimited queue and the second queue comprises a rate-controlled queue having a defined rate for processing received requests. Computing resource access requests from the user of the computing system are processed based on the defined rate for processing received requests.

Abstract: Certain aspects of the present disclosure provide techniques for a method of displaying a user interface on a mobile device, comprising: receiving a transaction file; performing text recognition on the transaction file to extract one or more transaction elements; determining a transaction characteristic based on the one or more transaction elements; displaying a transaction characteristic user interface element within an interactive cell displayed in the user interface; receiving a user touch gesture associated with the interactive cell via the user interface; and displaying an action user interface element in response to receiving the user touch gesture, wherein the action user interface element is configured to perform an action based on the transaction characteristic associated with the interactive cell.

Abstract: A method includes obtaining a help file including steps for a task and generating a knowledge graph including instructions corresponding to the steps. The method further includes extracting, from a user input of a user, an intent to complete the task. Responsive to extracting the intent to complete the task, obtaining the knowledge graph is obtained. Using the knowledge graph, an instruction of the knowledge graph is presented to perform an action in a workflow to complete the task.

Abstract: Systems and methods are disclosed for managing a generative artificial intelligence (AI) model to improve performance. Managing the generative AI model includes using a second generative AI model to generate outputs from similar inputs and comparing the outputs of the generative AI models to determine their similarity. The second generative AI model is trained using fresher training data but may not be manually supervised and adjusted to the level of the generative AI model being managed. As such, an output of the second generative AI model is compared to an output of the managed generative AI model by a classification model to determine a relevance of the output from the managed generative AI model. An output of the classification model is used to perform various suitable policies to optimize the performance of the managed generative AI model, such as providing alternate outputs, preventing providing the output, or retraining the model.

Abstract: Certain aspects of the present disclosure provide techniques for generating a replacement sentence with the same or similar meaning but a different sentiment than an input sentence. The method generally includes receiving a request for a replacement sentence and iteratively determining a next word of the replacement sentence word-by-word based on an input sentence. Iteratively determining the next word generally includes evaluating a set of words of the input sentence using a language model configured to output candidate sentences and evaluating the candidate sentences using a sentiment model configured to output sentiment scores for the candidates sentences. Iteratively determining the next word further includes calculating convex combinations for the candidate sentences and selecting an ending word of one of the candidate sentences as the next word of the replacement sentence. The method further includes transmitting the replacement sentence in response to the request for the replacement sentence.

Abstract: Certain aspects of the present disclosure provide techniques for committing log data in an application to a log data repository. An example method generally includes receiving, from an application, data to be committed to a remote storage location. A type of the received data is determined. The type of the received data is generally associated with a prioritization level and a compression mechanism to be used in committing the data to the remote storage location. An application execution context associated with the received data is determined. At a dispatch time associated with the prioritization level of the received data and the application execution context associated with the received data, a compressed data payload is generated and transmitted to the remote storage location. Generally, to compress the data payload, at least the received data is generally compressed based on the determined compression mechanism.

Abstract: Systems and methods for identifying and extracting specific product usage patterns of potential customers and utilizing a machine learning evaluation model to predict the potential customers that are most likely to convert their subscriptions.

Abstract: Certain aspects of the present disclosure provide techniques for rendering visual artifacts in virtual worlds using machine learning models. An example method generally includes identifying, based on a machine learning model and a streaming natural language input, an intent associated with the streaming natural language input; generating, based on the identified intent associated with the streaming natural language input, one or more virtual objects for rendering in a virtual environment displayed on one or more displays of an electronic device; and rendering the generated one or more virtual objects in the virtual environment.

Abstract: A method including receiving a natural language query from a user interface of a chatbot. The method also includes generating an input vector by performing vectorization on the natural language query. The method also includes inputting the input vector to a shallow-deep classifier. The shallow-deep learning classifier includes a classification machine learning model programmed to classify the input vector as being one of a shallow machine learning classification problem and a deep machine learning classification problem. The method also includes outputting, by the shallow-deep classifier, an output label. The output label includes one of the shallow machine learning classification problem and the deep machine learning classification problem.

Abstract: The disclosed embodiments provide a system that facilitates use of an application on an electronic device. During operation, the system obtains a first metadata definition containing a mapping of view components in a user interface of the application to a set of attribute-specific types associated with an attribute of the electronic device, and a second metadata definition containing a set of rules for binding the attribute-specific types to a set of platform-specific user-interface elements for a platform of the electronic device. Next, the system generates a view for display in the user interface by applying, based on the attribute and the platform, the first and second metadata definitions to content describing the view to select one or more platform-specific user-interface elements for rendering one or more of the view components in the content. The system then instantiates the platform-specific user-interface element(s) to render the view component(s).

Abstract: A method models and manages affinity networks. The method includes receiving real-time transaction data; processing a transaction of the real-time transaction data to identify a source node and a target node of a graph; and processing the transaction to update an affinity score of an edge from the source node to the target node. The method further includes receiving a request; selecting, responsive to the request, the target node using the affinity score after updating the affinity score; and presenting a response using the target node.