Abstract: A generative artificial intelligence (AI) model application programming interface (API) receives a generative AI request and routes the generative AI request to a generative AI model. The generative AI model API identifies whether the generative AI request is an asynchronous or a synchronous request and identifies a likely length of generation requested by the generative AI request. The generative AI model API evaluates the available capacity of generative AI models in a shared pool of computing system resources based upon the generative AI model type requested by the generative AI request and based upon the length of the requested generation. The generative AI model API routes the generative AI request to a generative AI model based upon the available capacity, whether the generative AI request is synchronous or asynchronous, the generative AI model type, and the length of the requested generation.

Abstract: A federated learning apparatus in a federated learning system includes: a model storage part that replicates and stores a shared model as a local model; a local training part that trains the local model by using data held by the federated learning apparatus; a secret sharing part that decomposes a local update parameter indicating a training result of the local model into shares based on an additive secret sharing scheme and distributes the shares to other federated learning apparatuses; an aggregation and secure computation part that performs a secure computation for shares of a global update parameter by performing addition of the shares of the local update parameters and multiplication of the shares by cleartext constants; and a global training part that reconstructs the shares of the global update parameter and updates the shared model by the global update parameter.

Abstract: A neural network construction method and apparatus in the field of artificial intelligence, to accurately and efficiently construct a target neural network. The constructed target neural network has high output accuracy, may be further applied to different application scenarios, and has a strong generalization capability. The method includes: obtaining a start point network, where the start point network includes a plurality of serial subnets; performing at least one time of transformation on the start point network based on a preset first search space to obtain a serial network, where the first search space includes a range of parameters used for transforming the start point network; and if the serial network meets a preset condition, training the serial network by using a preset dataset to obtain a trained serial network; and if the trained serial network meets a termination condition, obtaining a target neural network based on the trained serial network.

Abstract: A technique for dynamically updating a user interface for threat investigation may include receiving a scheduled transmittal of events in an event stream from an endpoint at a threat management facility, processing the event stream at the threat management facility to detect an intermediate threat, in response to detecting the intermediate threat at the threat management facility, requesting a transmittal of supplemental information from a data recorder on the endpoint, receiving the supplemental information in a supplemental transmittal from the endpoint to the threat management facility, and displaying a description of the intermediate threat and the supplemental information in a user interface hosted by the threat management facility, where the user interface is configured for user investigation and disposition of the intermediate threat.

Abstract: A computer-implemented method comprising: processing data in a neural network to compute a network tensor comprising a plurality of tensor elements represented in an initial numerical format; computing a histogram of tensor elements; selecting a target numerical format, the target numerical format having a lower precision than the initial numerical format; evaluating a metric based on the histogram of tensor elements and the target numerical format, the metric indicating a degree of accuracy of a representation of the network tensor in the target numerical format; and based on the evaluated metric, converting the plurality of tensor elements from the initial numerical format to the target numerical format.

Abstract: A system and method for controlling a nodal network. The method includes estimating an effect on the objective caused by the existence or non-existence of a direct connection between a pair of nodes and changing a structure of the nodal network based at least in part on the estimate of the effect. A nodal network includes a strict partially ordered set, a weighted directed acyclic graph, an artificial neural network, and/or a layered feed-forward neural network.

Abstract: A machine learning system includes a processor and a memory communicably coupled to the processor. The memory stores machine-readable instructions that, when executed by the processor, cause the processor to select a training dataset comprising training material compositions and tagged material property values, select at least two material property datasets comprising material compositions with corresponding material property values, and embed the training material compositions and the material compositions of the at least two material property datasets into a chemical space of a machine learning module. The memory also stores machine-readable instructions that, when executed by the processor, cause the processor to predict, based at least in part on the training material compositions and the material compositions of the at least two material property datasets embedded in the chemical space, property values for corresponding material compositions in the at least two material property datasets.

Abstract: In order to facilitate the entity resolution and entity activity tracking and indexing, systems and methods include receiving first source records from a first database and second source records from a record database. A candidate set of second source records is determined by a heuristic search in the set of second source records. A candidate pair feature vector associated with each candidate pair of first and second source records is generated. An entity matching machine learning model predicts matching first source records for each candidate second source record based on the respective candidate pair feature vector. An aggregate quantity associated with the matching first source records is aggregated from a quantity associated with each first source record, and a quantity index for each candidate second source record is determined based the aggregate quantities. Each quantity index is displayed to a user.

Abstract: Predictive analytics techniques are provided for produce leading indicators of economic activity based on observed pedestrian attributes—e.g., appearance and behavior—and other factors determined from a range of available data sources. A consistent, semantic metadata structure is described as well as a hypothesis generating and testing system capable of generating predictive analytics models in a non-supervised or partially supervised mode.

Abstract: Second machine learning models trained using respective second data sets can be received. The second machine learning models can be run using a first data set used in training a first machine learning model, where the second machine learning models produce respective outputs. Scores associated with the second machine learning models can be determined by comparing the respective outputs with ground truth associated with the first data set. Based on the scores associated with the second machine learning models, whether the first data set is to be discarded or kept can be determined for training the first machine learning model.

Abstract: Systems and methods for performing improper input data detection are described. In one example, a system comprises: hardware circuits configured to receive input data and to perform computations of a neural network based on the input data to generate computation outputs; and an improper input detection circuit configured to: determine a relationship between the computation outputs of the hardware circuits and reference outputs; determine that the input data are improper based on the relationship; and perform an action based on determining that the input data are improper.

Abstract: System and methods for adaptive multi-granularity event groupings are provided. In embodiments, a method includes: determining to group IT operations data at a first level of granularity for similar events or at a second level of granularity for related events based on user input of a data grouping event; parsing, by an event parser, the IT operations data into one or more groups of similar events based on text information and parser rules in response to determining to group the IT operations data at the first level of granularity; obtaining user feedback indicating the one or more groups of similar events require modification; determining one or more keywords of the IT operations data using an artificial intelligence model in response to the user feedback; and updating the parser rules for the event parser based on the one or more keywords, thereby generating updated parser rules.

Abstract: A system and method for for determining a degree of point cloud data degradation of a LiDAR sensor of a Self-Driving Car (SDC) using a machine-learning algorithm (MLA) are provided. The method comprises: determining, based on a training point cloud generated by the LiDAR sensor representative of surroundings of the SDC, a plurality of LiDAR features; determining, for each training object in the surroundings, based on statistical data of coverage of training objects with LiDAR points, a plurality of enrichment features; receiving a respective label indicative of a degradation degree of the training point cloud; generating, based on the plurality of LiDAR features, the plurality of enrichment features, and the respective label, a given feature vector of a plurality of feature vectors; training, based on the plurality of feature vectors, the MLA to determine an in-use degree of degradation of in-use sensed data further generated by the LiDAR sensor.

Abstract: Devices and techniques are generally described for local device embeddings for automation. In various examples, first data representing first state change data for network-connected computing devices configured in communication with a first network may be determined. The first data may be input into a first machine learning model. In some examples, the first machine learning model may generate first embedding data representing a combination of the first data and second data. In some examples, the second data may represent historical state change data for the network-connected devices. In some examples, the first embedding data may be stored in memory. A first action may be performed by a first network-connected device based at least in part on the first embedding data.

Abstract: A method for assessing the coherence of an input with a data processing system using synthesized concepts is provided. The method includes obtaining an active concept definition from the input of a cognitive agent, extracting real concept definitions composed of a set of attributes from an analyzed domain, matching the active concept definition to the extracted definitions, deriving virtual concept definitions from the real concept definitions using a semantic processing protocol such that the derived virtual concept definitions form a tree-structure graph of concepts and concept relationships, and measuring the attribute set coherence of the virtual concept definitions using a confidence gradient. The confidence gradient is based on at least one metric of relative proximity and co-occurrence. The method further includes assessing the probability of coherence, of the input with the data processing system, based on the measure of coherence within the confidence gradient.

Abstract: Aspects of the present disclosure are directed to systems, methods, and computer readable media for executing actions for events associated with use of applications. A computing system can identify data associated with an application to be evaluated for at least one of a plurality of events associated with a use of the application. The computing system can determine, based on applying the free text to a machine learning (ML) architecture, a value indicating a likelihood of occurrence of an event associated with the use of the application. The computing system can provide to a generative ML model, a model input based on the free data and the value. The computing system can execute an action corresponding to characterizing the event.

Abstract: A computer-implemented method, a computer program product, and a computer system for assessing fairness of a deep generative model. A computer system receives a user defined fairness criterion for the deep generative model. A computer system probes the deep generative model to produce samples for a target output. A computer system evaluates the samples for the fairness of the deep generative model, according to the user defined fairness criterion. A computer system produces a set of recommendations for modifying the deep generative model to meet the user defined fairness criterion, in response to determining that the deep generative model does not meet the user defined fairness criterion. In response to determining that the deep generative model is to be modified, a computer system applies at least one subset of the recommendations to the deep generative model. A computer system updates the deep generative model.

Abstract: Detecting anomalous data by applying a plurality of models to a data set to yield detection results including anomalous data, applying evaluation methods to the detection results for each of the plurality of models, determining a combined score for the detection results according to the evaluation methods, determining a combined score threshold, and defining a set of detected anomalies according to the combined score and the combined score threshold.

Abstract: A classifier network has at least two distinct sets of refined data, wherein the first two sets of refined data are sets of numbers representing the features values data received from sensors or a manufactured part. Performing, via at least two distinct types of support vector machines using an associated feature selection process for each classifier independently in a first layer, anomaly detection on the manufactured part. Then, using the stored data including refined data of at least two different types of data transforms and performing, via at least a two distinct types of support vector machines in a second layer, an associated feature selection process for each classifier independently. Forming at least four distinct compound classifier types for anomaly detection on the part using the stored data or coefficients. The ensemble of second layer support vector machine outputs compare the results to determine the presence of an anomaly.

Abstract: Systems and methods are provided for generating supplemental or updated machine learning models based on analysis of feature space data observed at inference time using an existing machine learning model.