Abstract: Systems and methods for training a machine learning model are disclosed. A system may be configured to obtain a plurality of training samples. The system includes a machine learning model to generate predictions and generate a confidence score for each generated prediction. In this manner, the system is configured to, for each training sample of the plurality of training samples, generate a prediction by a machine learning model based on the training sample and generating a confidence score associated with the prediction by the machine learning model. The system is also configured to train the machine learning model based on the plurality of predictions and associated confidence scores. For example, one or more training samples may be excluded from use in training the machine learning model based on the associated one or more confidence scores (such as the confidence score being less than a threshold).

Abstract: A method, apparatus, and computer-readable medium for efficiently optimizing a phenotype with a specialized prediction model, including receiving constraints, encoding genotype information in experimental data points corresponding to the constraints experiential genotype vectors, the experimental data points comprising the genotype information and phenotype information corresponding to the genotype information, training a phenotype prediction model based on the experiential genotype vectors, the corresponding phenotype information, and the one or more constraints, applying the phenotype prediction model to available genotypes corresponding to the constrains to generate scores, determining result genotypes based on a ranking of the available genotypes according to the scores, and generating, a result based on the result genotypes, the result indicating one or more genetic constructs for testing.

Abstract: Data is received which includes multimodal input for ingestion by a first generative AI (GenAI) model is received. This received data is input into the first GenAI model to result in a first output. The first output along with the received data is input into a second GenAI model to result in a second output. The first GenAI model is a modified (e.g., fine-tuned, etc.) version of the second GenAI model. When the second output indicates that guardrails associated with the second GenAI model have been triggered, one or more remediation actions are initiated. Otherwise, the first output is returned to the requestor. Related apparatus, systems, techniques and articles are also described.

Abstract: A method and system for selective transfer of organizational data in case of a divestiture are disclosed. The method includes: exporting a system architecture for a first database of a first organization from a first database of the first organization including data intended for migration from the first organization to a second organization; creating a second database of the second organization, which is a target database to which the intended data is to be transferred, in a system of the second organization by importing the exported system architecture to the system of the second organization; extracting the intended data from the first database; and sending the extracted intended data to the second database of the second organization.

Abstract: An automatic industry classification method comprises: determining a scope of target patents, defining a target industry tree; generating marks on the target industry tree; performing a rough classification for the target patents by using the marks; performing a fine classification for the target patents according to a result of the rough classification. The automatic industry classification method and system provided by the present invention uses a transductive learning method, so that full mining of small annotation quantity information is realized. The automatic industry classification method and system uses information of IPC, so that information dimension is enriched, and calculation amount needed in the classification is reduced. The automatic industry classification method and system further uses the hierarchical vectors generated by the abstract, the claims and the description, so that the information of word order relation is reserved, and the patent text is deeply mined.

Abstract: Systems and methods for using machine learning to extract data from electronic communications are disclosed. According to certain aspects, a machine learning model is trained on a set of tasks using a set of training data. An electronic communication indicating a purchase of a product and/or service is processed to generate augmented text that is input into the machine learning model. After analyzing the augmented text, the machine learning model outputs a set of predicted values for a set of defined categories, which an entity may use for various purposes such as to apply digital rewards to user accounts.

Abstract: Systems and methods for monitoring a network slice are provided. A method, according to one implementation, include extracting information from network traffic received from one or more User Plane Function (UPF) components of a network slice; examining the extracted information using Machine Learning (ML), and, in response to detecting of one or more malicious threats based on the examined extracted information by the ML, causing one or more actions to isolate the network traffic to protect at least the network slice from the one or more malicious threats.

Abstract: Systems and methods for computing a causal uplift in performance of an output action for one or more treatment actions in parallel are described herein. In an embodiment, a server computer receives interaction data for a particular period of time which identifies a plurality of users and a plurality of actions that were performed by each user of the plurality of users through a particular graphical user interface during the particular period of time. The server computer uses the interaction data to generate a feature matrix of actions for each user, and a set of confounding variables included to minimize spurious correlations. The feature matrix is then used to train a machine learning system, using data identifying a user's performance or non-performance of each action as inputs and data identifying performance or non-performance of a target output action as the output.

Abstract: A method, system, and computer program product for explaining predictions made by black box time series models. The method may include identifying a black box time series model. The method may also include predicting one or more time instances using the black box time series model. The method may also include selecting a predicted time instance from the predicted data. The method may also include receiving training data for the black box time series model. The method may also include generating a set of white box time series models similar to the black box time series model. The method may also include selecting a preferred white box time series model. The method may also include analyzing behavior of the preferred white box time series model. The method may also include generating an explanation illustrating why the black box time series model forecasted the predicted time instance.

Abstract: In some implementations, a data aggregator may receive an indication associated with a data record. The data aggregator may apply a model to the indication to generate a prediction regarding when new information associated with the data record will be available. Based on the prediction, the data aggregator may refrain from requesting new information and may schedule a pull for new information associated with the data record for a later time. Additionally, or alternatively, the data aggregator may receive an indication associated with a plurality of data pulls that are associated with a plurality of data records and may receive an indication of a rate limit associated with a host for the plurality of data records. The data aggregator may apply rules to generate a ranking of the plurality of data pulls and may schedule the plurality of data pulls based on the ranking and the rate limit.

Abstract: Systems and methods are provided for selecting training examples to increase the efficiency of supervised active machine learning processes. Training examples for presentation to a user may be selected according to measure of the model's uncertainty in labeling the examples. A number of training examples may be selected to increase efficiency between the user and the processing system by selecting the number of training examples to minimize user downtime in the machine learning process.

Abstract: A system and method for accelerated content classification and routing of digital files in a data handling and data governance service includes identifying a digital computer file; sequentially routing the digital computer file to one or more machine learning-based content classification models of a plurality of distinct machine learning-based content classification models based on a service-defined model instantiation and execution sequence, wherein: the service-defined model instantiation and execution sequence defines a model instantiation and execution order for the plurality of distinct machine learning-based content classification models that enables a fast content classification of the digital computer file while minimizing a computation time or runtime of the one or more machine learning-based content classification models; computing, via a machine learning-based filename classification model, a content classification inference based on extracted filename feature data of the digital computer file; and

Abstract: Aspects presented herein may enable wireless communications to be adaptive to a dynamic environment, where wireless devices may manage wireless communications, such as performing beam managements, based at least in part on environmental conditions. In one aspect, a network entity receives, from a sensor device or a UE, a request for an ML data service. The network entity establishes, with the sensor device or the UE, the ML data service based on the request. The network entity receives, from the sensor device, ML data including a set of features extracted from at least one sensor of the sensor device or information indicative of at least one beam for the ML data service. The network entity transmits, to the UE, a beam indication to modify the at least one beam based at least in part on the ML data received from the sensor device during the ML data service.

Abstract: A computer implemented methods for estimating at least one quality function of a given layered coating on a transparent substrate allows to predict at least one non in-process measured quality function of a given layered coating on a transparent substrate from an in-process measured quality function which can be acquired on the coated substrate as deposited at any location, preferably at the end of a coating process. The method allows to get rid of in-process real-time continuous measurements of quality functions of the coated transparent substrate and real-time monitoring of coating process parameters.

Abstract: A computer-implemented method includes receiving a request for generating a simulation scenario or digital media that includes one or more entities and one or more assets in an environment, the request including contextual information. The method further includes selecting three-dimensional (3D) digital twins based on the contextual information, wherein one or more of the 3D digital twins correspond to the assets, one or more of the 3D digital twins correspond to the one or more entities, and one of the 3D digital twins corresponds to the environment. The method further includes generating the simulation scenario that initializes the 3D digital twins and establishes a spatial relationship between the 3D digital twins based on the contextual information. The method further includes controlling behavior of the 3D digital twins in the simulation scenario based on the contextual information.

Abstract: A system for identification of a fraudulent voice call in real-time is described. The system includes a first device configured to receive a voice call originating from a second device and generate a call forward request. A server is configured to, in response to the call forward request, divide the voice call into a plurality of audio signals and analyze one or more audio signals to identify whether an audio originating from the second device is a cloned voice or a human voice. The server is configured to analyze the audio signal along with one or more preceding audio signals to determine a risk score associated with an identification of a fraudulent activity during the voice call and identify the voice call as the fraudulent voice call. The server is configured to trigger an alert in the first device to indicate that the voice call is a fraudulent voice call.

Abstract: Various embodiments of the present technology generally relate to industrial automation environments. More specifically, embodiments include systems and methods to visualize machine learning model status in an industrial automation environment. In some examples, a machine learning component receives process inputs associated with industrial devices in the industrial automated environment. The machine learning component processes the inputs to generate machine learning outputs and transfers the machine learning outputs to influence one or more functions of the industrial devices. The machine learning component reports operational data characterizing the machine learning outputs. A Human Machine Interface (HMI) component displays a visualization of the machine learning component and receives the operational data from the machine learning component.

Abstract: Systems and methods are described for building artificial intelligence (“AI”) pipelines. A user interface (UI) includes selectable pipeline objects, such as a dataset and an AI model, that a user can position and connect on the screen. This causes execution linking between the selected pipeline objects, with the execution linking being visually displayed in the UI. A management policy can be applied to the pipeline, including user or device requirements for accessing the dataset in the pipeline. Then the UI can present a simulated execution of the AI pipeline, in which a test query is input and the pipeline objects execute in an order displayed in the UI. The pipeline can then be deployed for access at an endpoint.

Abstract: Techniques for determining system performance without ground truth include receiving a trained model and one or more generator models, the trained model having been trained on training data. The trained model is used on testing data to produce labeled testing data, and the labeled testing data are used to train a proxy model. The one or more generator models are used to produce synthetic training data that are representative of the training data. The proxy model is used on the synthetic training data to produce predictions, and performance of the trained model is determined based on the predictions by the proxy model.

Abstract: This document describes a method for identifying anomaly constructs in real-time based on multimodal surveillance data, the identification being done using a multimodal sensory and cognitive abstraction module. Meta-descriptors are generated for the surveillance data and subsequently, meta-descriptor embeddings are generated for the meta-descriptors whereby the meta-descriptor embeddings are used by an anomaly assertion model to detect anomaly constructs within the surveillance data.

Abstract: A computer-implemented method for processing data which are associated for example with a signal transmittable and/or transmitted via a bus system, for example of a vehicle, including: at least intermittent provision of reference data for a statistical model which characterizes at least one average of at least one characteristic of the signal on the basis of a first average determined, for example dynamically, over a predefinable unweighted first number of values for the characteristic, and at least intermittent modification of the reference data at least in part on the basis of a second average determined, for example dynamically, over a predefinable weighted second number of values for the characteristic.

Abstract: A secured exploration agent for reinforcement learning (RL) is provided. Securitizing an exploration agent includes training the exploration agent to avoid dead-end states and dead-end trajectories. During training, the exploration agent “learns” to identify and avoid dead-end states of a Markov Decision Process (MDP). The secured exploration agent is utilized to safely and efficiently explore the environment, while significantly reducing the training time, as well as the cost and safety concerns associated with conventional RL. The secured exploration agent is employed to guide the behavior of a corresponding exploitation agent. During training, a policy of the exploration agent is iteratively updated to reflect an estimated probability that a state is a dead-end state. The probability, via the exploration policy, that the exploration agent chooses an action that results in a transition to a dead-end state is reduced to reflect the estimated probability that the state is a dead-end state.

Abstract: An exemplary method for reducing bias in a training image dataset for training a machine-learning model comprises: receiving a plurality of text strings comprising at least one text string describing each image in the training image dataset; generating a plurality of embeddings based on the plurality of text strings; identifying, based on the plurality of embeddings, a plurality of visual features in the training image dataset; identifying one or more correlations between the plurality of visual features in the training image dataset; receiving a user input identifying at least one biased correlation from the one or more correlations; and training the machine-learning model at least partially by adjusting one or more data sampling weights associated with one or more training images in the training image dataset based on the user input.

Abstract: A prompt for a generative artificial intelligence (GenAI) model is received which includes unicode. Unicode fonts in the prompt are identified and then translated into a plaintext representation. Further, unicode characters in the prompt are identified which each have an associated unicode tag. It is determined, based on the associated unicode tags, whether at least a portion of the unicode characters are valid. When at least a portion of the unicode characters are determined to be valid, the unicode characters in the prompt are converted into a plaintext representation. The prompt with the translated fonts and the converted unicode fonts are passed into the GenAI model. When at least a portion of the unicode characters are not determined to be valid, the unicode characters are removed from the prompt. This prompt with the translated unicode fonts, after the unicode characters are removed, is input into the GenAI model.

Abstract: A computer system for mapping products to taxability categories includes one or more processors configured to execute, in a run-time inference phase, an artificial intelligence model, a taxability category mapping engine, and a taxability category driver record association engine. The artificial intelligence model is configured to receive product text including a product name and product description associated with a product catalog, and output a predicted tax category for a product associated with the product catalog. The taxability category mapping engine is configured to link a taxability driver to the product. The taxability category driver record association engine is configured to create a taxability category mapping drivers record including the taxability driver that is linked to the product. The predicted tax category output from the artificial intelligence model and the taxability category mapping drivers record are stored in a product taxability record.

Abstract: Aspects of the present disclosure are directed to systems, methods, and computer readable media for regulating digital therapeutic content for provision. A computing system may identify a digital therapeutic content to be provided via a network. The computing system may apply the digital therapeutic content to a machine learning (ML) model having a set of weights. The computing system may determine, from applying the digital therapeutic content to the ML model, an indication as of one of compliance or non-compliance. The computing system may store, using one or more data structures, an association between the digital therapeutic content and the indication used to control provision of the digital therapeutic content via the network, by (i) restricting the digital therapeutic content from provision responsive to determining the indication of non-compliance and (ii) permitting the digital therapeutic content to be provided responsive to determining the indication of compliance.

Abstract: Aspects relate to system and methods for determining a user specific mission operational performance, using machine-learning processes.

Abstract: One embodiment of the present invention sets forth a technique for curating a data sample set. The technique includes determining one or more data sampling criteria based on a sampling objective for a data sample set associated with the machine learning model. The technique also includes selecting, from a set of unlabeled data samples, at least one data sample to be labeled and added to a data sample set associated with the machine learning model based on the one or more data sampling criteria. The technique also includes, for each selected data sample, supplementing the data sample set with the selected data sample and at least one association with a label.

Abstract: A method including extracting data from disparate data sources. The data includes data pairs including a corresponding data point and a corresponding time associated with the corresponding data point. The method also includes extracting insights from the data at least by identifying a trend in the data pairs. The method also includes forming a model vector including the insights and an additional attribute to the insights. The additional attribute characterizes the insights. The additional attribute includes at least user feedback including a user ranking of a ranked subset of the insights from a user. The method also includes inputting the model vector into a trained insight machine learning model to obtain a predicted ranking of the insights. The method also includes selecting, based on the predicted user ranking, a pre-determined number of insights to form predicted relevant insights. The method also includes reporting the predicted relevant insights.

Abstract: A computing system and method can be used to implement a version of federated learning (FL) that incorporates adaptivity (e.g., leverages an adaptive learning rate). In particular, the present disclosure provides a general optimization framework in which (1) clients perform multiple epochs of training using a client optimizer to minimize loss on their local data and (2) a server system updates its global model by applying a gradient-based server optimizer to the average of the clients' model updates. This framework can seamlessly incorporate adaptivity by using adaptive optimizers as client and/or server optimizers. Building upon this general framework, the present disclosure also provides example specific adaptive optimization techniques for FL which use per-coordinate methods as server optimizers. By focusing on adaptive server optimization, the use of adaptive learning rates is enabled without increase in client storage or communication costs and compatibility with cross-device FL can be ensured.

Abstract: A data set can be provided that includes an input data element and one or more label data portion definitions that each identify a feature of interest within the input data element. A machine-learning model can generate model-identified portions definitions that identify predicted feature of interests within the input data element. At least one false negative (where a feature of interest is identified without a corresponding predicted feature of interest) and at least one false positive (where a predicted feature of interest is identified without a corresponding feature of interest) can be a identified. A class-disparate loss function can be provided that is configured to penalize false negatives more than at least some false positives. A loss can be calculated using the class-disparate loss function. A set of parameter values of the machine-learning model can be determined based on the loss.

Abstract: Embodiments described herein provide visual-and-language (V+L) systems and methods for learning vision and language representations. Specifically, a method may comprise receiving a training dataset comprising a plurality of image samples and a plurality of text samples; encoding the plurality of image samples into a plurality of encoded image samples and the plurality of text samples into a plurality of encoded text samples; computing a first loss objective based on the plurality of encoded image samples and the plurality of encoded text samples; encoding a first subset of the plurality of encoded image samples and a second subset of the plurality of encoded text samples into a plurality of encoded image-text samples; computing a second loss objective based on the plurality of encoded image-text samples; and updating the V+L model based at least in part on the first loss objective and the second loss objective.

Abstract: A platooning control device includes: a learning device configured to perform reinforcement learning on the basis of image information and a feedback signal and to control a pertinent vehicle so as to follow a traveling trajectory of a front vehicle according to a result of the reinforcement learning; and a compensation determination unit configured to receive a coordinate of a control point regarding the traveling trajectory of the front vehicle from the front vehicle and to compare a coordinate of the pertinent vehicle with the coordinate of the control point, thereby generating the feedback signal.

Abstract: Techniques described herein relate to a method for managing a distributed multi-tiered computing (DMC) environment. The method includes obtaining, by a global controller, a DMC environment management request from a user, whereas the DMC environment management request is associated with scheduling an application in the DMC environment; and in response to obtaining the request: identifying target domains for tasks associated with the application based on the request; selecting scheduling policies for each target domain; obtaining fingerprints of previously provisioned applications associated with the request; performing case based reasoning using the fingerprints to generate scheduling packages for the target domains; sending the scheduling packages to local controllers associated with the target domains; obtaining application information from the local controllers; and providing the application information to the user.

Abstract: In some examples, a node for a telecommunication network includes a neural-network-based receiver for uplink communications. The node is configured to modify the neural-network-based receiver to generate a set of modified receiver frameworks defining respective different versions for the receiver, using each of the modified receiver frameworks, generate respective measures representing bits encoded by a signal received at the node, calculate a value representing a variance of the measures, and on the basis of the value, determine whether to select the signal received at the node for use as part of a training set of data for the neural-network-based receiver.

Abstract: A computer-implemented method is provided for policy evaluation. In the method, the utility of the given decision-making policy is estimated based on a dataset of state-action-reward-state tuples, a set of candidate bootstrapping estimators of the fitted Q-evaluation (FQE) algorithm, and a criterion function. The method automatically selects the best bootstrapping estimator from the candidates based on the criterion function and, when the criterion function is appropriately designed, it produces a good policy-value estimate such that the estimation error is small (below a threshold).

Abstract: An adaptive quantum signal processor (AQSP) includes a signal combiner, a physics station, a measurement system, a machine-learning engine and an output generator. The signal combiner combines incoming signals with control functions to yield recipe functions. For example, the recipe functions can be “shaking” functions used to change the wavefunctions of atoms entrained in an optical lattice. The recipe functions are applied to wavefunctions in initial wavefunction states causing the wavefunctions to transition to signal-impacted states. The measurement system measures the wavefunctions in their signal-impacted quantum states to yield wavefunction characterizations. The machine-learning engine updates control functions based on the wavefunction characterizations. The output generator outputs results based on the wavefunction characterizations and/or control function characterizations. In a matched-filter application, the outputs characterize (e.g., identify, classify, rate) the incoming signals.

Abstract: A system for determining whether inconsistencies exist in an entity's shared databases using a machine learning model. The system includes a repository having a plurality of databases that store data and information in a format accessible to users, and a back-end server operatively coupled to the repository and being responsive to the data and information from all of the databases. The back-end server includes a processor for processing the data and information, a communications interface communicatively coupled to the processor, and a memory device storing data and executable code. The code causes the processor to collect data and information from the databases, store the collected data and information in the memory device, process the stored data and information through the machine learning model to determine whether inconsistencies in the data exist in the databases, and transmit a communication on the interface identifying whether inconsistencies do exist in the databases.

Abstract: Methods, systems, and computer programs are presented for eliminating bias while training an ML model using training data that includes past experimental data. One method includes accessing experiment results, for A/B testing of a first model, that comprise information regarding engagement with a first set of items presented to users, each item being presented within an ordered list of results. A position bias is calculated for positions within the ordered list of results where the items were presented. A machine-learning program is trained to obtain a second model using a training set comprising values for features that include the calculated position bias. The method includes detecting a second set of items to be ranked for presentation to a first user, and calculates, using the second model, a relevance score for the second set of items, which are ranked based on the respective relevance score and presented on a display.

Abstract: A systematic explainer is described herein, which comprises local, model-agnostic, surrogate ML model-based explanation techniques that faithfully explain predictions from any machine learning classifier or regressor. The systematic explainer systematically generates local data samples around a given target data sample, which improves on exhaustive or random data sample generation algorithms. Specifically, using principles of locality and approximation of local decision boundaries, techniques described herein identify a hypersphere (or data sample neighborhood) over which to train the surrogate ML model such that the surrogate ML model produces valuable, high-quality information explaining data samples in the neighborhood of the target data sample.

Abstract: A system and method for performing machine learning in a mobile computing device which is configured to be coupled with a cloud computing system is disclosed. The method may include activating, on the mobile computing device, a machine learning application, which accesses a local machine learning system including a local machine learning model, periodically updating the local machine learning system based upon updates for the local machine learning system received from a global machine learning system hosted by the cloud computing system, performing machine learning based on received training data, and periodically transmitting changes to the local machine learning system from the mobile computing device to the global machine learning system hosted by the cloud computing system.

Abstract: Systems and methods for operating a quantum processor. The methods comprise: receiving a reward matrix at the quantum processor, the reward matrix comprising a plurality of values that are in a given format and arranged in a plurality of rows and a plurality of columns; converting, by the quantum processor, the given format of the plurality of values to a qubit format; performing, by the quantum processor, subset summing operations to make a plurality of row selections based on different combinations of the values in the qubit format; using, by the quantum processor, the plurality of row selections to determine a normalized quantum probability for a selection of each row of the plurality of rows; making, by the quantum processor, a decision based on the normalized quantum probabilities; and causing, by the quantum processor, operations of an electronic device to be controlled or changed based on the decision.

Abstract: In some embodiments, a service platform that facilitates artificial intelligence model and data collection and collection may be provided. Input/output information derived from machine learning models may be obtained via the service platform. The input/output information may indicate (i) first items provided as input to at least one model of the machine learning models, (ii) first prediction outputs derived from the at least one model's processing of the first items, (iii) second items provided as input to at least another model of the machine learning models, (iv) second prediction outputs derived from the at least one other model's processing of the second items, and (v) other inputs and outputs. The input/output information may be provided via the service platform to update a first machine learning model. The first machine learning model may be updated based on the input/output information being provided as input to the first machine learning model.

Abstract: A computer-implemented method for performing Learning from Demonstrations, particularly Imitation Learning, based on data associated with a first domain, particularly a source domain. The method includes: determining first data characterizing a demonstrator of the first domain, wherein particularly the first data characterizes sensor data of the demonstrator and/or sensor data of at least one spectator observing the demonstrator, determining first knowledge from the first domain based on the first data, transferring at least a part of the first knowledge to a second domain, particularly a target domain.

Abstract: Disclosed examples include an automated online experimentation mechanism that can perform model selection from a large pool of models with a relatively small number of online experiments. The probability distribution of the metric of interest that contains the model uncertainty is derived from a Bayesian surrogate model trained using historical logs. Disclosed techniques can be applied to identify a superior model by sequentially selecting and deploying a list of models from the candidate set that balance exploration-exploitation.

Abstract: Aspects of the disclosure relate to intelligent bot performance tracking and analysis. A computing platform may receive a work queue of items to be processed using a bot. The computing platform may receive, in real-time with processing of the work queue using the bot, metadata associated with the work queue. Based on the metadata, the computing platform may assign, in real-time, a value metric associated with completion of each item in the work queue. Based on the assigned value metric, the computing platform may identify a robotic process automation cost associated with processing the work queue via the bot. The computing platform may compare, the robotic process automation cost to a cost to process the work queue via another operation, and determine a performance metric for the bot based on the comparison. The computing platform may dynamically generate and transmit, in real-time, an indication of the determined bot performance metric.

Abstract: An AI-based platform for enabling intelligent orchestration and management of power and energy is disclosed. The platform includes a digital twin system having a digital twin of a mining environment. The digital twin includes at least one parameter that is detected by a sensor of the mining environment. In some disclosed embodiments, the at least one parameter is associated with one or more of an unmined portion of the mining environment a mining of materials from the mining environment, a smart container event involving a smart container associated with the mining environment, a physiological status of a miner associated with the mining environment, a transaction-related event associated with the mining environment, and a compliance of the mining environment with one or more contractual, regulatory, and/or legal policies.

Abstract: A method of retrieving a document according to an embodiment of the present application includes: acquiring a user retrieval query; calculating a user inquiry vector in a unit of sentence from the user retrieval query and acquiring a first document candidate group based on similarity between the calculated user inquiry vector and an embedding vector of a document stored in a retrieval database; acquiring a second document candidate group based on similarity between a text included in the user retrieval query and a text of the document stored in the retrieval database; and determining a summarization target document based on the first document candidate group and the second document candidate group.

Abstract: A data processing service facilitates the creation and processing of data processing pipelines that process data processing jobs defined with respect to a set of tasks in a sequence and with data dependencies associated with each separate task such that the output from one task is used as input for a subsequent task. In various embodiments, the set of tasks include at least one cleanroom task that is executed in a cleanroom station and at least one non-cleanroom task executed in an execution environment of a user where each task is configured to read one or more input datasets and transform the one or more input datasets into one or more output datasets.

Abstract: There is provided a system and method of runtime examination of a semiconductor specimen. The method includes obtaining a runtime image representative of an inspection area of the specimen, the runtime image having a relatively low signal-to-noise ratio (SNR); and processing the runtime image using a machine learning (ML) model to obtain examination data specific for a given examination application, wherein the ML model is previously trained for the given examination application using one or more training samples, each training sample representative of a respective reference area sharing the same design pattern as the inspection area and comprising: a first training image of the respective reference area having a relatively low SNR; and label data indicative of ground truth in the respective reference area pertaining to the given examination application, the label data obtained by annotating a second training image of the respective reference area having a relatively high SNR.