Resumen de: US2023081540A1

Examples of methods for media classification are described herein. In some examples, a method includes analyzing text associated with media using a first machine learning model to produce a first result. In some examples, the method includes analyzing numerical metadata associated with the media using a second machine learning model to produce a second result. In some examples, the method includes inputting the first result and the second result to a third machine learning model to determine a classification of the media.

Resumen de: WO2023036714A1

A computer-implemented method comprising: obtaining activity data indicative of an anomalous activity within a computer system; processing the activity data to generate confidence data representative of a set of confidence values, each confidence value representative of a confidence that the anomalous activity comprises a respective type of activity; and determining, based on at least the confidence data, mitigating action to take to mitigate the anomalous activity. Further examples relate to a computer system configured to implement an intrusion detection system and an intrusion response system, and to a computer-implemented method of calibrating a system comprising a machine learning model trained to generate output uncalibrated confidence data representative of a set of output uncalibrated confidence values.

Resumen de: GB2610562A

A method of obtaining activity data indicative of an anomalous activity within a computer system 102, processing the activity data to generate confidence data that represent a confidence that the anomalous activity is a respective type of activity 104, and determining mitigating action based on the confidence data 106. There is also a second invention of calibrating a system with a machine learning model trained to generate output uncalibrated confidence data by processing calibration activity data representative of an anomalous activity, computing an uncertainty metric associated with the set of uncalibrated confidence values, and adjusting parameters associated with the ML model based on the uncertainty metric. The confidence data may be calibrated confidence data, the confidence values may be calibrated confidence values. Processing the activity data may be performed using a machine learning model to generate initial confidence data that represents a set of initial confidence values.

Resumen de: US2023075295A1

According to an aspect of an embodiment, operations may include receiving an ML project including a data-frame and an ML pipeline including a plurality of code statements associated with a plurality of features corresponding to the ML project. The operations may further include determining one or more atomic steps corresponding to the ML pipeline to determine an atomized ML pipeline. The operations may further include instrumenting the atomized ML pipeline to determine an instrumented ML pipeline including one or more operations corresponding to the ML project. The operations may further include executing the instrumented ML pipeline to capture one or more data-frame snapshots based on each of the one or more operations. The operations may further include constructing a feature provenance graph (FPG). The operations may further include identifying one or more discarded features, from the plurality of features corresponding to the ML project, based on the constructed FPG.

Resumen de: US2023072878A1

Methods, apparatus, and processor-readable storage media for automated topology-aware deep learning inference tuning are provided herein. An example computer-implemented method includes obtaining input information from one or more systems associated with a datacenter; detecting topological information associated with at least a portion of the systems by processing at least a portion of the input information, wherein the topological information is related to hardware topology; automatically selecting one or more of multiple hyperparameters of at least one deep learning model based on the detected topological information; determining a status of at least a portion of the detected topological information by processing, during an inference phase of the at least one deep learning model, the detected topological information and data from at least one systems-related database; and performing, in connection with at least a portion of the selected hyperparameters, one or more automated actions based on the determining.

Resumen de: US2023072862A1

A machine learning (ML) model publisher can, responsive to an indication that a ML model is ready for publication, generate a publication request form or page on a user device. The ML model publisher can be invoked from within a ML modeling application. Responsive to an instruction received through the publication request form or page, the ML model publisher can access a data structure in memory used in training the ML model and populate the publication request form or page with attributes required by the ML model to run. Responsive to activation of a single-click publication actuator, the ML model publisher can publish the ML model directly from the ML modeling application to a target computing system by providing, to the target computing system, a path to a repository location where the ML model is stored and information on the attributes required by the ML model to run.

Resumen de: US2023073197A1

A method of reducing a power consumption of wireless communication circuitry of an edge device according to one embodiment includes determining a delivery traffic indication map (DTIM) interval of a wireless access point communicatively coupled to the edge device via the wireless communication circuitry of the edge device and adjusting a wake-up interval of the wireless communication circuitry of the edge device based on the DTIM interval to reduce the power consumption of the wireless communication circuitry of the edge device.

Resumen de: US2023072966A1

Systems and methods for processing and using sensor data. The methods comprise: obtaining semantic labels assigned to data points; performing a supervised machine learning algorithm and an unsupervised machine learning algorithm to respectively generate a first confidence score and a second confidence score for each semantic label of said semantic labels, the first and second confidence scores each representing a degree of confidence that the semantic label is correctly assigned to a respective one of the data points; generating a final confidence score for each said semantic label based on the first and second confidence scores; selecting subsets of the data points based on the final confidence scores; and aggregating the data points of the subsets to produce an aggregate set of data points.

Resumen de: WO2023033843A1

Techniques for identifying a root cause of an operational result of a deterministic machine learning model are disclosed. A system applies a deterministic machine learning model to a set of data to generate an operational result, such as a prediction of a "fault" or "no-fault" in the system. The set of data includes signals from multiple different data sources, such as sensors. The system applies an abductive model, generated based on the deterministic machine learning model, to the operational result. The abductive model identifies a particular set of data sources that is associated with the root cause of the operational result. The system generates a human-understandable explanation for the operational result based on the identified root cause.

Resumen de: US2023074788A1

Machine learning to predict a layout type that each of a plurality of portions of a document appears in. This is done even though the computer-readable representation of the document does not contain information at the granularity of the prediction to be made that identifies which layout type that each of the plurality of document portions belongs in. For each of a plurality of the portions, the machine-learning system predicts the layout type that the respective portion appears in, and indexes the document using the predictions so as to result in a computer-readable index. The index represents a predicted layout type associated with each of the plurality of portions of the document. Thus, the index can be used to search based on position of a searched term within the document.

Resumen de: US2023074025A1

A plurality of initial machine learning models are determined based on a plurality of original features. The plurality of initial machine learning models are filtered by selecting a subset of the initial machine learning models as one or more surviving machine learning models. One or more evolved machine learning models are generated. At least one of the evolved machine learning models is based at least in part on one or more new features, which are based at least in part on a transformation of at least one of features of the one or more surviving machine learning models. Corresponding validation scores associated with the one or more evolved machine learning models and corresponding validation scores associated with the one or more surviving machine learning models are compared. At least one of the one or more evolved machine learning models or the one or more surviving machine learning models are selected as one or more new selected surviving machine learning models.

Resumen de: US2023074056A1

The described systems and methods determine a driver's fitness to safely operate a moving vehicle based at least in part upon observed impairment patterns. A smart ring, wearable on a user's finger, continuously monitors impairment levels. This impairment data, representing impairment patterns, can be utilized, in combination with driving data, to train a machine learning model, which will predict the user's level of risk exposure based at least in part upon observed impairment patterns. The user can be warned of this risk to prevent them from driving or to encourage them to delay driving. In some instances, the disclosed smart ring system may interact with the user's vehicle to prevent it from starting while the user is in a state of impairment induced by substance intoxication.

Resumen de: US2023075812A1

A computer system has a first machine learning module configured to predict a probability of a respective option being selected by a particular user if presented to that user via a computer app. A second machine learning module is configured to determine a respective confidence value associated with the probability. A third module uses the predicted probabilities and confidence values to determine at least one option to be presented to the particular user.

Resumen de: AU2021332209A1

A model is trained through a hybrid machine learning process. In the hybrid machine landing process, an automatic machine learning process is performed on a dataset to generate a model for making a prediction. The automatic machine learning process uses a pipeline to train the model and makes decisions in the steps of the pipeline. After the model is trained through the automatic machine learning process, a representation of the pipeline is generated and presented to a user in a user interface. The user interface allows the user to modify at least some decision made in the automatic machine learning process. One or more modifications are received from the user through the user interface and are used to refine the trained model. The refined model is deployed to make the prediction based on new data.

Resumen de: US2023075196A1

A disclosed example includes aggregating first performance results of computer-generated machine learning models to generate aggregated performance results, the first performance results based on a comparison of audience member demographic data to training results, the training results generated by the computer-generated machine learning models based on at least one of: (a) a composition of a household, (b) a type of first media, (c) a daypart during which the first media was accessed, or (d) a time at which the first media was accessed; selecting at least one of the computer-generated machine learning models based on a comparison of ones of the first performance results to the aggregated performance results; and applying the at least one of the computer-generated machine learning models to correct a computer-generated error in computer-collected audience measurement data, the computer-collected audience measurement data corresponding to accesses to second media.

Resumen de: US2023075424A1

Systems and methods are disclosed for a decision tree processing system. A machine learning decision tree architecture, such as a Random Forest, can be very intense in computation and can require a large amount of memory. To account for such, the systems and methods herein can implement a hardware approach where the training for the decision trees can be performed in advance via firmware (or an algorithm implemented via any other software and processing system) and the hardware can implement a circuit to process the decision trees. In some examples, multiple decision trees may be processed in parallel. Also, a circuit can compute the best outcome for a decision tree based on a random feature and a pre-determined threshold for the random feature assigned to each node of the decision tree.

Resumen de: EP4145357A1

According to an aspect of an embodiment, operations may include receiving an ML project including a data-frame and an ML pipeline including a plurality of code statements associated with a plurality of features corresponding to the ML project. The operations may further include determining one or more atomic steps corresponding to the ML pipeline to determine an atomized ML pipeline. The operations may further include instrumenting the atomized ML pipeline to determine an instrumented ML pipeline including one or more operations corresponding to the ML project. The operations may further include executing the instrumented ML pipeline to capture one or more data-frame snapshots based on each of the one or more operations. The operations may further include constructing a feature provenance graph (FPG). The operations may further include identifying one or more discarded features, from the plurality of features corresponding to the ML project, based on the constructed FPG.

Resumen de: EP4145361A1

According to an aspect of an embodiment, operations may include receiving an ML project stored in an ML corpus database. The operations may further include mutating a first ML pipeline, of a set of first ML pipelines associated with the received ML project, to determine a set of second ML pipelines. The mutation of the first ML pipeline may correspond to a substitution of a first ML model associated with the first ML pipeline with a second ML model associated with one of the set of predefined ML pipelines. The operations may further include selecting one or more ML pipelines from the set of second ML pipelines based on a performance score associated with each of the determined set of ML pipelines. The operations may further include augmenting the ML corpus database to include the selected one or more ML pipelines and the set of first ML pipeline.

Resumen de: EP4145356A1

The present disclosure relates to a constrained optimization computer-implemented method for gradient boosting machines. In various embodiments, a process for constrained optimization for sequential error-based additive machine learning models (e.g., gradient boosting machines) includes configuring a sequential error-based additive machine learning model, receiving training data, and using one or more hardware processors to train the sequential error-based additive machine learning model using the received training data. The training includes performing optimization iterations to minimize a loss function that includes a fairness constraint, where the fairness constraint is based at least in part on disparities between groups.

Resumen de: GB2610543A

Techniques for refinement of data pipelines are provided. An original file of serialized objects is received, and an original pipeline comprising a plurality of transformations is identified based on the original file. A first computing cost is determined for a first transformation of the plurality of transformations. The first transformation is modified using a predefined optimization, and a second cost of the modified first transformation is determined. Upon determining that the second cost is lower than the first cost, the first transformation is replaced, in the original pipeline, with the optimized first transformation.

Resumen de: US2023062793A1

Embodiments described herein are directed to intelligently classifying Web trackers in a privacy preserving manner and mitigating the effects of such Web trackers. As users browse the Web and encounter various Web sites, tracker-related metrics are determined. The metrics are obfuscated to protect the privacy of the user. The obfuscated metrics are provided as inputs to a machine learning model, which is configured to output a classification for the Web trackers associated with the Web sites visited by the user. Depending on the classification, the effects of the Web trackers are mitigated by placing restrictions on the Web trackers. The restrictions for a particular Web tracker may be relaxed based on a level of user engagement a user has with respect to the tracker's associated Web site. By doing so, the compatibility risks associated with tracking prevention are mitigated for Web sites that are relatively important to the user.

Resumen de: WO2023025552A1

Systems and methods to intelligently optimize data collection requests are disclosed. In one embodiment, systems are configured to identify and select a complete set of suitable parameters to execute the data collection requests. In another embodiment, systems are configured to identify and select a partial set of suitable parameters to execute the data collection requests. The present embodiments can implement machine learning algorithms to identify and select the suitable parameters according to the nature of the data collection requests and the targets. Moreover, the embodiments provide systems and methods to generate feedback data based upon the effectiveness of the data collection parameters. Furthermore, the embodiments provide systems and methods to score the set of suitable parameters based on the feedback data and the overall cost, which are then stored in an internal database.

Resumen de: US2023061280A1

Techniques for identifying a root cause of an operational result of a deterministic machine learning model are disclosed. A system applies a deterministic machine learning model to a set of data to generate an operational result, such as a prediction of a “fault” or “no-fault” in the system. The set of data includes signals from multiple different data sources, such as sensors. The system applies an abductive model, generated based on the deterministic machine learning model, to the operational result. The abductive model identifies a particular set of data sources that is associated with the root cause of the operational result. The system generates a human-understandable explanation for the operational result based on the identified root cause.

Resumen de: US2023066706A1

Systems, devices, and methods for training an automated agent are disclosed. Multiple automated agents are instantiated, each of the automated agents configured to train over a plurality of training cycles. For each resource, a dedicated portion of a memory device to store state data for the respective resource is allocated. The method includes receiving a request for state data for a particular resource from a subset of the automated agents; for each of the training cycles for the subset of the plurality of automated agents, storing updated state data for the particular resource in the dedicated portion of the memory device allocated to the particular resource; and transmitting an address of the dedicated portion of the memory device for the particular resource to the subset of the automated agents, to facilitate asynchronous reading of the stored state data for the particular resource during each training cycle.

Resumen de: US2023064674A1

The present disclosure relates to a computer receiving a current training dataset. A first fraction of the training dataset comprises synthetic training data and a remaining second fraction of the training dataset comprising real-life training data. The real-life training data is user defined data and the synthetic training data is system defined data. A machine learning based engine is trained and may repeatedly be performed by using the current training dataset. In each iteration or a subset of the iterations, the training dataset is updated by adding real-life training data, thereby increasing the second fraction in the updated training dataset and reducing the first fraction of the synthetic training data.