Abstract: An optimization apparatus (100) includes a setting unit (110) that sets a predetermined non-linear objective function, a policy determination unit (120) that determines a policy to be executed in online optimization in a bandit problem, based on the non-linear objective function, a policy execution unit (130) that acquires a reward as an execution result of the determined policy, an update rate determination unit (140) that determines an update rate of the non-linear objective function by a multiplicative weight update method, based on the acquired reward and the non-linear objective function, and an update unit (150) that updates the non-linear objective function, based on the update rate.

Abstract: Custom source code generation models are generated by tuning a pre-trained deep learning model by freezing the model parameters and optimizing a prefix. The tuning process is distributed across a user space and a model space where the embedding and output layers are performed in the user space and the execution of the model is performed in a model space that is isolated from the user space. The tuning process updates the embeddings of the prefix across the separate execution spaces in a manner that preserves the privacy of the data used in the tuning process.

Abstract: The present system relates a platform for addressing the optimal privacy-accuracy trade-off in the revelation of a user's valuable information to a third party. Specifically, the present system formalizes the privacy-accuracy trade-off in a precise mathematical framework, wherein mathematical formalization captures user's privacy preference with a single parameter. The system possesses a revelation method of user data that is optimal, in the sense of abiding by user's privacy preference while providing the most accurate description to third party subject to the aforementioned privacy preference constraint.

Abstract: Systems, methods, and apparatuses for detecting and identifying anomalous data in an input data set are provided.

Abstract: An example operation may include one or more of generating a hashed summary including hashes of one or more of a validation data set and hashes of data points chosen in previous iterations from producer nodes, and exposing the hashed summary to a plurality of producer nodes, receiving, iteratively, a plurality of requests from the plurality of producer nodes, respectively, where each request identifies a marginal value provided by a hash of a data sample available to a producer node, selecting a request received from a producer node based on a marginal value associated with the request, retrieving hashed data of the producer node associated with the selected request, and aggregating the hashed data of the producer node with the summary of hashes generated at one or more previous iterations to produce an updated summary, and storing the updated summary via a data block of a distributed ledger.

Abstract: The present disclosure provides various approaches for smart area monitoring suitable for parking garages or other areas. These approaches may include ROI-based occupancy detection to determine whether particular parking spots are occupied by leveraging image data from image sensors, such as cameras. These approaches may also include multi-sensor object tracking using multiple sensors that are distributed across an area that leverage both image data and spatial information regarding the area, to provide precise object tracking across the sensors. Further approaches relate to various architectures and configurations for smart area monitoring systems, as well as visualization and processing techniques. For example, as opposed to presenting video of an area captured by cameras, 3D renderings may be generated and played from metadata extracted from sensors around the area.

Abstract: A method of providing sentiment analysis includes training a computer system to identify a polarity of a sentiment for a plurality of phrases and receiving, at the computer system, an input from a website. The input includes a text string including a phrase. The method includes determining, by the computer system, the polarity of the sentiment of the phrase by comparing the phrase to the plurality of phrases and sending, by the computer system, a command to the website that causes the website to display predetermined content based on the determined polarity of the sentiment of the phrase.

Abstract: One or more computing devices, systems, and/or methods are provided. A machine learning model may be trained using a plurality of sets of information. One or more pruning operations may be performed in association with the training to generate a machine learning model with sparse vector representations associated with features of the plurality of sets of information. A request for content associated with a client device may be received. A set of features associated with the request for content may be determined. A plurality of positive signal probabilities associated with a plurality of content items may be determined using the machine learning model based upon one or more sparse vector representations, of the machine learning model, associated with the set of features. A content item may be selected from the plurality of content items for presentation via the client device based upon the plurality of positive signal probabilities.

Abstract: An automation method of an artificial intelligence (AI)-based diagnostic technology for equipment application includes receiving one or more pieces of data among vibration data, noise data, and controller area network (CAN) data, a data input processing operation of trimming the input data, an operation of extracting features from the trimmed data, setting a setting value of a hyper-parameter with respect to the one or more pieces of data thereamong, and generating a total of N models to include both of machine learning (ML) and deep learning (DL) as N individual models and generating ensemble prediction model structures for the N individual models. As a parameter updating is being proceeded due to the hyper-parameter so as to minimize values of cost functions of the N individual models, a reward for model accuracy performance is optimized and the ensemble prediction model structures of the N individual models change.

Abstract: An information processing device according to the present invention includes: a memory; and at least one processor coupled to the memory. The processor performs operations. The operations includes: extracting a feature of a period or a frequency in a plurality of pieces of time-series data acquired by measuring an object; classifying the pieces of time-series data into a group related to the feature; generating, for each of the groups, a model that represents a relationship among the pieces of time-series data classified into the group; and selecting the model in which strength of the relationship satisfies a predetermined condition.

Abstract: An inference apparatus provides target data to multiple inference models to cause the inference models each derived from local learning data obtained in a different environment to perform predetermined inference to obtain an inference result from each of the inference models. The inference apparatus determines the value of each combining parameter using environment data, weights the inference result from each of the inference models using the determined value of each combining parameter, and combines the weighted inference result from each inference model together to generate an inference result in a target environment.

Abstract: A system and a method for image-based crop identification are disclosed. The image-based crop identification system includes a database, a communication module and a model library. The database stores sample aerial data and annotated aerial data. The communication module is coupled to the database, and is configured to provide the sample aerial data to a user and receive the annotated aerial data from the user. The model library is coupled to the database, and is configured to obtain the annotated aerial data, train a crop classification model based on the annotated aerial data, and provide the trained crop classification model for subsequent crop identification. The annotated aerial data include determination of the type of the crop appearing in the sample aerial data.

Abstract: A method of determining a thermal maturity model of a subterranean region of interest is disclosed. The method includes obtaining a plurality of rock samples for the subterranean region of interest. The method further includes determining a first porosity value, a second porosity value, and a volume fraction of organic matter, for each of the plurality of rock samples. The method further includes determining, for each of the plurality of rock samples, a thermal maturity index based, at least in part, on the first porosity value, the second porosity value and the volume fraction of organic matter. The method further includes determining the thermal maturity model based, at least in part, on the thermal maturity index for each of the plurality of rock samples.

Abstract: One or more computer processors create a binary cluster of events by bootstrapping a set of ground truths contained with a rule engine applied to a set of high-dimensional datapoints, wherein the binary cluster contains two clusters each containing a plurality of high-dimensional datapoints; determine one or more peer groups for a set of unknown high-dimensional datapoints utilizing a trained multiclass classifier, wherein the high-dimensional datapoints are assigned to one or more peer groups by the trained multiclass classifier using an incremental learning algorithm in order to reduce system resources; create an activity distribution for each unknown high-dimensional datapoint associated with a user in the set of unknown high-dimensional datapoints and each peer group; calculate a deviation percentage between the activity distribution of the user and each peer group associated with the user; and responsive to exceeding a deviation threshold, classify the user or associated high-dimensional datapoints as ri

Abstract: One or more computing devices, systems, and/or methods for determining activity patterns based upon user activity and/or performing operations based upon the activity patterns are provided. For example, activity performed using a communication interface associated with a user account may be detected. The activity may be analyzed to determine an activity pattern associated with a first set of conditions. The activity pattern may be stored in a user profile associated with the user account. The user profile may comprise a plurality of activity patterns. Each activity pattern of the plurality of activity patterns may be associated with a set of conditions of a plurality of sets of conditions. It may be determined that the first set of conditions are met. Responsive to determining that the first set of conditions are met, one or more operations associated with the activity pattern may be performed.

Abstract: Vehicular in-cabin facial tracking is performed using machine learning. In-cabin sensor data of a vehicle interior is collected. The in-cabin sensor data includes images of the vehicle interior. A set of seating locations for the vehicle interior is determined. The set is based on the images. The set of seating locations is scanned for performing facial detection for each of the seating locations using a facial detection model. A view of a detected face is manipulated. The manipulation is based on a geometry of the vehicle interior. Cognitive state data of the detected face is analyzed. The cognitive state data analysis is based on additional images of the detected face. The cognitive state data analysis uses the view that was manipulated. The cognitive state data analysis is promoted to a using application. The using application provides vehicle manipulation information to the vehicle. The manipulation information is for an autonomous vehicle.

Abstract: Methods for anomaly detection using dictionary based projection (DBP), and system for implementing such methods. In an embodiment, a method comprises receiving input data including a plurality n of multidimensional data points (MDDPs) with dimension m, applying DBP iteratively to the input data to construct a dictionary D, receiving a newly arrived MDDP (NAMDDP), calculating a score S associated with the NAMDDP as a distance of the NAMDDP from dictionary D, and classifying the NAMDDP as normal or as an anomaly based on score S, wherein classification of the NAMDDP as an anomaly is indicative of detection of an unknown undesirable event.

Abstract: An abduction apparatus 1 includes: a probability calculation unit 2 configured to, with respect to each of candidate hypotheses generated using observation information and knowledge information, calculate a probability that the candidate hypothesis holds true as an explanation of the observation information; and a reward selection unit 3 configured to, when the candidate hypothesis holds true, select a reward value regarding the candidate hypothesis that has held true by referring to reward definition information in which a condition that the candidate hypothesis holds true is associated with the reward value.

Abstract: Techniques are disclosed to predict medical device failure based on operational log data. Log data associated with a plurality of devices comprising a population of devices each having a same target part subject to failure. For each of at least a subset of the plurality of devices replacement dates on which the target part was replaced in that device are determined. A set of logged event data with prescribed severity is extracted from the log data for said plurality of devices. A subset of the logged event data is identified as being associated with impending failure of the target part. The subset of the logged event data is transformed into a normalized form. The normalized subset of the logged event data is used to generate a failure prediction model to predict failure of the target part in a device based on the current event logs from that device.

Abstract: Disclosed are various embodiments for using decision trees for machine-learning when data is missing from a data set. A first attribute for splitting a plurality of records is identified. Then, the plurality of records are split into a first subset of records and a second subset of records. The first subset of records can include each of the plurality of records where a value is present for the first attribute and the second subset of records comprising each of the plurality of records where the value is absent for the first attribute. Finally, a node can be added to a decision tree that reflects the split of the plurality of records into the first subset of records and the second subset of records.

Abstract: An apparatus includes a memory and a processor. The memory stores descriptions of known vulnerabilities and information generated by a monitoring subsystem. Each description of a known vulnerability identifies software components that are associated with the known vulnerability. The monitoring subsystem monitors software programs that are installed within a computer system. The information includes descriptions of issues that are associated with the software programs. The processor generates a set of mappings, based on a comparison between the text describing the known software vulnerabilities and the text describing the issues. Each mapping associates a software program that is associated with an issue with a known software vulnerability. The processor also uses a machine learning algorithm to predict that a given software program is associated with a particular software vulnerability.

Abstract: Methods and systems are presented for analyzing feedback data associated with a content and generating an interactive graphical representation of the feedback data. Upon receiving a request from a user, a feedback analysis system may access feedback data associated with a content from a content hosting server. The feedback data may include comments submitted by viewers of the content. The feedback analysis system may analyze the comments and generate an interactive graphical representation of the feedback data. The interactive graphical representation may include icons that represents keywords that are relevant to the comments and sentiments of the viewers derived based on the comments. Upon receiving a selection of an icon, the feedback analysis system may present a comment that corresponds to the keyword and/or sentiment represented by the icon.

Abstract: Methods, systems and computer program products are described to improve machine learning (ML) model-based classification of data items by identifying and removing inaccurate training data. Inaccurate training samples may be identified, for example, based on excessive variance in vector space between a training sample and a mean of category training samples, and based on a variance between an assigned category and a predicted category for a training sample. Suspect or erroneous samples may be selectively removed based on, for example, vector space variance and/or prediction confidence level. As a result, ML model accuracy may be improved by training on a more accurate revised training set. ML model accuracy may (e.g., also) be improved, for example, by identifying and removing suspect categories with excessive (e.g., weighted) vector space variance. Suspect categories may be retained or revised. Users may (e.g., also) specify a prediction confidence level and/or coverage (e.g., to control accuracy).

Abstract: The present application provides a model training, image processing method, device, storage medium, and program product relating to deep learning technology, which are able to screen auxiliary image data with image data for learning a target task, and further fuse the target image data and the auxiliary image data, so as to train a built and to-be-trained model with the fusion-processed fused image data. This implementation can increase the amount of data for training the model, and the data for training the model is determined is based on the target image data, which is suitable for learning the target task. Therefore, the solution provided by the present application can train an accurate target model even if the amount of target image data is not sufficient.

Abstract: Techniques for generating a set of Deep Learning (DL) models are described. An example method includes training an initial set of DL models using the training data, wherein a topology of each of the DL models is determined based on the parameters vector. The method also includes generating a set of estimate performance functions for each of the DL models in the initial set based on the set of edge-related metrics, and generating a plurality of objective functions based on the set of estimated performance functions. The method also includes generating a final DL model set based on the objective functions, receiving a user selection of a selected DL model from the final DL model set, and deploying the selected DL model to an edge device.

Abstract: A system and method are disclosed that utilizes an artificial intelligence based virtual proxy node. The virtual proxy node includes an intent resolution model and communicates between a smart audio device and at least one secondary device, wherein the at least one secondary device is configured to be controlled by a smart audio device or smart hub. The virtual proxy node tracks interactions between the smart audio device and the at least one secondary device to derive historical and context data from the tracking interactions. The virtual proxy node uses the historical and context data to predict which secondary device will be successful in responding to the user input command and broadcasts the input command to the virtual proxy node associated with one of the at least one secondary device. The virtual proxy node includes an intent resolution model trained by historical and context data.

Abstract: Described are systems and methods for establishing a unit group dictionary based on user provided annotations. The unit group dictionary may be used to identify relationships between multiple items in a corpus. Those relationships may facilitate the display of object identifiers and/or other aspects used and/or provided by the object management service.

Abstract: Embodiments of systems and methods for enhanced drift remediation with causal methods and online model modification are described. In some embodiments, an Information Handling System (IHS) may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution, cause the IHS to: detect drift in an Artificial Intelligence (AI) or Machine Learning (ML) model configured to make a prediction or a causal reasoning graphical or structural inference based upon input data, identify a root cause of the drift, and tag the input data with an indication of the root cause.

Abstract: The present invention relates to a non-invasive cardiac monitoring device that records cardiac data to infer physiological characteristics of a human, such as cardiac arrhythmia. Some embodiments of the invention allow for long-term monitoring of physiological signals. Further embodiments allow for processing of the detected cardiac rhythm signals partially on the wearable cardiac monitor device, and partially on a remote computing system. Some embodiments include a wearable cardiac monitor device for long-term adhesion to a mammal for prolonged detection of cardiac rhythm signals.

Abstract: A method includes receiving a point data anomaly detection query from a user. The query requests the data processing hardware to determine a quantity of anomalous point data values in a set of point data values. The method includes training a model using the set of point data values. For at least one respective point data value in the set of point data values, the method includes determining, using the trained model, a variance value for the respective point data value and determining that the variance value satisfies a threshold value. Based on the variance value satisfying the threshold value, the method includes determining that the respective point data value is an anomalous point data value. The method includes reporting the determined anomalous point data value to the user.

Abstract: 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.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining causal models for controlling environments. One of the methods includes repeatedly selecting control settings for the environment based on (i) a causal model that identifies causal relationships between possible settings for controllable elements in the environment and environment responses that reflect a performance of the control system in controlling the environment and (ii) current values of a set of internal parameters; and during the repeatedly selecting: monitoring environment responses to the selected control settings; determining, based on the environment responses, an indication that one or more properties of the environment have changed; and in response, modifying the current values of one or more of the internal parameters.

Abstract: An information processing apparatus having a first fitness calculation to calculate a fitness using a predetermined function for models in a population; a virtual model generating to select, as parent models, models having higher value of the fitness using the first fitness calculation among the models, and generate a virtual model that outputs by performing calculation of output results of the selected parent models; a second fitness calculation to calculate the fitness of the virtual model using the predetermined function; a replacing operation constituting the population by adding the virtual model and by deleting a model having lower value of the fitness among the models in the population; and a model extracting to extract a model having higher value of the fitness from the population by repeating processing by the virtual model generating, the second fitness calculation, and the model replacing until a predetermined termination condition is reached.

Abstract: A calculation device receives input of a plurality of pieces of training data including a communication destination known to be malignant as data. The calculation device generates a model that calculates a malignant degree of an input communication destination from each piece of the training data. The calculation device gives weight to each of the models, and generates a mixed model using the model and the weight. The calculation device calculates a malignant degree of a communication destination unknown whether the communication destination is malignant using the mixed model.

Abstract: Techniques for implementing unsupervised anomaly detection by self-prediction are provided. In one set of embodiments, a computer system can receive an unlabeled training data set comprising a plurality of unlabeled data instances, where each unlabeled data instance includes values for a plurality of features. The computer system can further train, for each feature in the plurality of features, a supervised machine learning (ML) model using a labeled training data set derived from the unlabeled training data set, receive a query data instance, and generate a self-prediction vector using at least a portion of the trained supervised ML models and the query data instance, where the self-prediction vector indicates what the query data instance should look like if it were normal. The computer system can then generate an anomaly score for the query data instance based on the self-prediction vector and the query data instance.

Abstract: A system detects and responds to malicious acts directed towards machine learning models. Data fed into and output by a machine learning model is collected by a sensor. The data fed into the model includes vectorization data, which is generated from raw data provided from a requester, such as for example a stream of timeseries data. The output data may include a prediction or other output generated by the machine learning model in response to receiving the vectorization data. The vectorization data and machine learning model output data are processed to determine whether the machine learning model is being subject to a malicious act (e.g., attack). The output of the processing may indicate an attack score. A response for handling the request by a requester may be selected based on the output that includes the attack score, and the response may be applied to the requestor.

Abstract: A model lifecycle management method includes: executing a model initial development phase based on at least a first criteria, a second criteria, and a third criteria to obtain a set of production ready models; executing, using the set of production ready models, a model production phase based on at least a fourth criteria, a fifth criteria, and a sixth criteria to obtain; and executing, after executing the model production phase, using the set of models to be updated, a model update phase based on at least a seventh criteria on at least one model in the model production phase.

Abstract: An Artificial Intelligence (AI)-based data processing system processes current data to determine if the quality of the current data is adequate to be provided to data consumers and if the quality is adequate, the current data is further analyzed to determine if an impacted load including changes to dimension data of the current data or an incremental load including changes to fact data of the current data is to be provided to the data consumers. Depending on the amount of data to be provided to the data consumers, processing units (PUs) may be determined and assigned to carry out the data upload. Various machine learning (ML) models that are used to provide predictions from the current data are analyzed to determine the quality of predictions and if needed, can be automatically retrained by the data processing system.

Abstract: Process evolution for robotic process automation (RPA) and RPA workflow micro-optimization are disclosed. Initially, an RPA implementation may be scientifically planned, potentially using artificial intelligence (AI). Embedded analytics may be used to measure, report, and align RPA operations with strategic business outcomes. RPA may then be implemented by deploying AI skills (e.g., in the form of machine learning (ML) models) through an AI fabric that seamlessly applies, scales, manages AI for RPA workflows of robots. This cycle of planning, measuring, and reporting may be repeated, potentially guided by more and more AI, to iteratively improve the effectiveness of RPA for a business. RPA implementations may also be identified and implemented based on their estimated return on investment (ROI).

Abstract: Aspects of the present disclosure enable humanly-specified relationships to contribute to a mapping that enables compression of the output structure of a machine-learned model. An exponential model such as a maximum entropy model can leverage a machine-learned embedding and the mapping to produce a classification output. In such fashion, the feature discovery capabilities of machine-learned models (e.g., deep networks) can be synergistically combined with relationships developed based on human understanding of the structural nature of the problem to be solved, thereby enabling compression of model output structures without significant loss of accuracy. These compressed models provide improved applicability to “on device” or other resource-constrained scenarios.

Abstract: A network device divided into a training plane and a control plane, model management server that controls a network device, and processing methods of a network device and model management server are disclosed. A processing method may include receiving a machine learning model from a model management server, obtaining network data to generate analytics information, generating analytics information by inputting the network data to a machine learning model, feeding back the analytics information to the model management server, and generating a control command of the network device using the analytics information, wherein the analytics information is generated by a training plane function and the control command is generated by a control plane function.

Abstract: The present invention discloses a collaborative design method using an event-triggered scheme (ETS) and a Takagi-Sugeno (T-S) fuzzy H? controller in a network environment. For the problem about the unmanned surface vehicle control based on a switching T-S fuzzy system under an aperiodic DoS attack, the present invention provides an H? controller design method based on the event-triggered scheme. The characteristics of the unmanned surface vehicle system under the DoS attack are analyzed, and external disturbance in the navigation process is added into an unmanned surface vehicle motion model to establish an unmanned surface vehicle switching system model. The stability of the system is analyzed by piecewise Lyapunov functionals, such that controller gain and event-triggered scheme weight matrix parameters are obtained, thus ensuring that a networked unmanned surface vehicle navigation system has the ability to resist the DoS attack and the external disturbance.

Abstract: A control device includes an exterior panel comprising multiple regions, including a groove region and a surrounding region that surrounds the groove region. The control device further includes a sensor layer comprising one or more sensors to detect touch inputs performed on the groove region and the surrounding region of the exterior panel. The control device further includes a control module configured to operate a plurality of devices. The control module is configured to detect a first touch input performed by a user on the groove region and a second touch input performed on the surrounding region. Based at least in part on the location of the touch inputs the control module operates respective devices of the plurality of devices.

Abstract: A search method using an artificial intelligence based information retrieval model and a method for training the artificial intelligence based information retrieval model used for the method are provided. In the method, even if there is no labeled data and only a corpus exists, the artificial intelligence based information retrieval model can be trained using the weak-supervision methodology. Search can be performed by dividing documents into passages having short lengths. Compared to an information retrieval model based on unsupervised learning, improved search results are provided.

Abstract: A computer-based method, system, and computer program product for automatically identifying significant events for food traceability. The method may comprise receiving a series of events from an agriculture supply chain entity, automatically determining, at a machine learning model of an event analysis module, one or more events in the series having a significance for food traceability greater than a threshold, and automatically reporting the one or more events to a ledger.

Abstract: Described herein are embodiments of a reinforcement learning based large-scale multi-objective ranking system. Embodiments of the system may be used for optimizing short-video recommendation on a video sharing platform. Multiple competing ranking objective and implicit selection bias in user feedback are the main challenges in real-world platform. In order to address those challenges, multi-gate mixture of experts (MMoE) and soft actor critic (SAC) are integrated together into a MMoE_SAC system. Experiment results demonstrate that embodiments of the MMoE_SAC system may greatly reduce a loss function compared to systems only based on single strategies.

Abstract: Disclosed herein is a method of a communication device operating in a wireless communication network for managing power consumption of the device. The device is configured to operate according to first, second and third operational states for communication with a network node associated with the communication network.

Abstract: Techniques are described for providing an IT and security operations mobile application for managing IT and security operations instances of an IT and security operations application via a mobile device. The IT and security operations mobile application can be linked to the IT and security operations application to enable the IT and security operations application to send messages (e.g., notifications, alerts, action requests, etc.) related the occurrences of incidents/events in an IT environment, such as security-related incident, that can impact the operation of the IT environment. The IT and security operations mobile application enables a user to respond to the messages by initiating actions that are sent to the IT and security operations application for executing within the IT environment.

Abstract: A method for monitoring performance of a ML system includes receiving a data stream via a processor and generating a first plurality of metrics based on the data stream. The processor also generates input data based on the data stream, and sends the input data to a machine learning (ML) model for generation of intermediate output and model output based on the input data. The processor also generates a second plurality of metrics based on the intermediate output, and a third plurality of metrics based on the model output. An alert is generated based on at least one of the first plurality of metrics, the second plurality of metrics, or the third plurality of metrics, and a signal representing the alert is sent for display to a user via an interface.

Abstract: A computer-implemented method includes: receiving an inquiry request message identifying a first payment transaction having a plurality of transaction parameters and a risk score, where the risk score is generated by a machine-learning model based on the plurality of transaction parameters; for each transaction parameter of the plurality of transaction parameters, perturbing a value of the transaction parameter and re-analyzing the first payment transaction with the machine-learning model to generate a perturbed risk score based on the perturbed transaction parameter; determining at least one impact parameter from the plurality of transaction parameters by comparing the perturbed risk scores generated for each of the plurality of transaction parameters; and generating an inquiry response message based on the at least one impact parameter.