Abstract: As described herein, a system, method, and computer program are provided for a machine-learning model-agnostic cloud-agnostic no-code onboarding platform. In use, a universal unified interface to a Model-Agnostic Onboarding Workflow (MAOW) platform is provided, wherein the MAOW platform is configured as a no-code, model-agnostic, cloud-agnostic platform. Additionally, at least one machine learning model is onboarded using the MAOW platform, based on the universal unified interface. Further, the at least one machine learning model is deployed from the MAOW platform to at least one target environment.

Abstract: This application provides an airspace complexity evaluation method based on deep unsupervised learning for air traffic management, which includes the following parts. A stacked autoencoder is used to establish an airspace complexity evaluation model. Input the airspace complexity factors into the stacked autoencoder to obtain the low-dimensional embedded representations of the airspace complexity factors. Cluster the low-dimensional embedded points to capture the centroids of the airspace complexity data. The application utilizes the soft assignment distribution and real assignment distribution of the embedded representations to construct a training loss function which optimizes the airspace complexity evaluation model by gradient descent algorithm. The trained airspace complexity evaluation model and the three obtained cluster centroids describing the airspace complexity level are used to evaluate the current airspace complexity.

Abstract: Data samples are transmitted from a central server to at least one local server apparatus. The central server receives a set of predictions from the at least one local server apparatus that are based on the transmitted set of data samples. The central server trains a central model based on the received set of predictions. The central model, or a portion of the central model corresponding to a task of interest, can then be sent to the at least one local server apparatus. Neither local data from local sites nor trained models from the local sites are transmitted to the central server. This ensures protection and security of data at the local sites.

Abstract: A monitoring system implements a method for versatile and efficient detection and grading of deviations in packaging containers for liquid food in a manufacturing plant. The method comprises obtaining image data of a packaging container, or a starting material for use in producing the packaging container; analyzing the image data for detection of a current deviation; processing the current deviation in relation to a set of basis functions, which is associated with a deviation type of the current deviation, to obtain a current set of weights that represent the current deviation; and determining a current grading of the current deviation based on the current set of weights. The set of basis function may be pre-computed based on reproductions of packaging containers or starting material comprising different magnitudes of the deviation type.

Abstract: Techniques for using scoring algorithms utilizing containers for flexible machine learning inference are described. In some embodiments, a request to host a machine learning (ML) model within a service provider network on behalf of a user is received, the request identifying an endpoint to perform scoring using the ML model. An endpoint is initialized as a container running on a virtual machine based on a container image and used to score data and return a result of said scoring to a user device.

Abstract: Provided are systems for ensemble learning with machine learning models that include a processor to receive a training dataset of a plurality of data instances, wherein each data instance comprises a time series of data points, add an amount of time delay to one or more data instances to provide an augmented training dataset, select a first plurality of supervised machine learning models, select a second plurality of unsupervised machine learning models, train the first plurality of supervised machine learning models and the second plurality of unsupervised machine learning models based on the augmented training dataset, generate an ensemble machine learning model based on outputs of the supervised machine learning models and unsupervised machine learning models, and generate a runtime output of the ensemble machine learning model based on a runtime input to the ensemble machine learning model. Methods and computer program products are also provided.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed that coordinate network traffic between a wireless network device and a computing platform. An example apparatus includes a wake-up selector to generate a target wait time parameter based on a workload type of a number of packets obtained from a network device and a user preference, the target wait time parameter indicative of a time interval that, when met, causes a modem to retrieve the number of packets, a data frame generator to generate a data frame that causes the network device to buffer the number of packets for the time interval, and a network packet controller to negotiate, using the data frame, the target wait time parameter with a network device.

Abstract: A method and apparatus for the pruning of a neural network is provided. The method sets a weight threshold value based on a weight distribution of layers included in a neural network, predicts a change of inference accuracy of a neural network by pruning of each layer based on the weight threshold value, determines a current subject layer to be pruned with a weight threshold value among the layers included in the neural network, and prunes a determined current subject layer.

Abstract: Implementations for determining content perception by a participant in a media session by analyzing content are described. A content signal, such as an audio signal or a video signal, is received during a media session. A transcript of the content can be determined. Feedback, such as a pre-determined phrase, related to content perception by a participant in the media session is determined using a learning algorithm at the device. Metadata regarding the media session is collected in response to the feedback related to the content perception. The indication of the feedback related to the content perception and the metadata regarding the media session is then sent. In response, one or more adjustments to the media session are received. The one or more adjustments to the media session can be determined based on the indication of the feedback related to the content perception, the metadata regarding the media session, and network performance information.

Abstract: Method of predicting a response of a subject to food is disclosed. The method comprises: selecting a food to which a response of the subject is unknown; accessing a first database having data describing the subject but not a response of the subject to the selected food; accessing a second database having data pertaining to responses of other subjects to foods, the responses of the other subjects including responses of at least one other subject to the selected food or a food similar to said selected food; and analyzing the databases based on the selected food to estimate the response of the subject to the selected food.

Abstract: Aspects of the invention include creating a neural network including neurons to which actions are assigned in representation of test cases. Tests of various instantiations of the neural network are executed for each test case and a state of the neural network after each test is evaluated to determine a fitness score of a corresponding instantiation. Instantiations having fitness scores that exceed a predefined level and identified and the instantiations having the fitness scores that exceed the predefined level are selected for adjustments. The executing, the evaluating, the identifying and the selecting are iteratively repeated in order to obtain desired fitness scores.

Abstract: Systems and methods for personal data classification, linkage and purpose of processing prediction are provided. The system for personal data classification includes an entity extraction module for extracting personal data from one or more data repositories in a computer network or cloud infrastructure, a linkage module coupled to the entity extraction module, a linkage module coupled to the entity extraction module and a processing prediction module. The entity extraction module performs entity recognition from the structured, semi-structured and unstructured records in the one or more data repositories. The linkage module uses graph-based methodology to link the personal data to one or more individuals.

Abstract: Aspects concern a method for controlling a transport system comprising determining historical data of a multiplicity of transport trips performed by the transport system, training a neural network to perform an invertible mapping of transport trips to latent representations to fulfil, by the distribution of the latent representations of the multiplicity of transport trips, a predetermined fitting criterion with respect to a predetermined latent representation base distribution, sampling a multiplicity of latent representations from the base distribution, mapping each of the sampled latent representations to a respective transport trip by using the trained neural network to perform the inverse of the invertible mapping to generate a multiplicity of synthetic transport trips, determining a control scheme for the transport system using the multiplicity of synthetic transport trips and controlling the transport system using the determined control scheme.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing predictive mapping operations with respect to a ground-truth database table. Certain embodiments of the present invention utilize systems, methods, and computer program products that perform predictive mapping operations utilizing a hierarchical string matching machine learning framework using at least one or more of an exact match model, a probabilistic match model, a disjoint match model, and an embedding-based match model.

Abstract: An apparatus for determining a hierarchical listing of information gaps for a user is provided. The apparatus includes a processor and a memory connected to the processor. The memory contains instructions configuring the processor to receive an instance of an identification datum from a user device, where the identification datum describes an output type from the user device at a time, receive a target status datum from a database connected to the processor, where the target status datum describes an optimal output type between a minimal output type and a maximum output type, and to classify the identification datum and the target status datum to categories representing identification data. The processor may identify an instance of a gap between identification data and display an input field to the user capable of displaying a hierarchical listing of information gaps based on a user-input datum.

Abstract: The present teaching relates to method, system, medium, and implementation of in-situ perception in an autonomous driving vehicle. A plurality of types of sensor data are acquired continuously via a plurality of types of sensors deployed on the vehicle, where the plurality of types of sensor data provide information about surrounding of the vehicle. One or more items surrounding the vehicle are tracked, based on some models, from a first of the plurality of types of sensor data from a first type of the plurality of types of sensors. A second of the plurality of types of sensor data are obtained from a second type of the plurality of sensors and are used to generate validation base data. Some of the one or more items are labeled, automatically, via validation base data to generate labeled at least some item, which is to be used to generate model updated information for updating the at least one model.

Abstract: A driving assistance method includes: detecting a position of a first obstacle ahead of a host vehicle on a first lane where the host vehicle is traveling; detecting a position of a second obstacle ahead of the host vehicle on a second lane, the second lane being an oncoming lane adjacent to the first lane; when the position of the second obstacle is on a nearer side than the position of the first obstacle in a traveling direction of the host vehicle, determining a first stop position as a stop position of the host vehicle to a position before the second obstacle in the traveling direction of the host vehicle; and assisting the host vehicle to stop at the determined first stop position.

Abstract: A system and methods for OCD metrology are provided including receiving training data for training an OCD machine learning (ML) model, including multiple pairs of corresponding sets of scatterometric data and reference parameters. For each of the pairs, one or more corresponding outlier metrics are by calculated and corresponding outlier thresholds are applied whether a given pair is an outlier pair. The OCD MIL model is then trained with the training data less the outlier pairs.

Abstract: Systems, methods, and computer-readable media are disclosed for generating and training a deep convolutional generative model for multivariate time series modeling and utilizing the model to assess time series data indicative of a machine or machine component's operational state over a period of time to detect and localize potential operational anomalies.

Abstract: Various examples described herein are directed to systems and methods that retrieve data from an information source. The data includes a first data set for a party and a second data set. The second data set has an entity associated with the party and a role of the party at the entity. The first data set is stored at a database and the second data set is stored at a cross-reference table associated with the database. A data request for requested information is received and the first data set is retrieved from the database. The second data set is retrieved from the cross-reference table based on the first data set. A hierarchical structure is created based on the second data set, where the hierarchical structure has different lists based on one of the entity and the role of the party at the entity.

Abstract: Various image diagnostic systems, and methods of operating thereof, are disclosed herein. Example embodiments relate to operating the image diagnostic system to identify one or more tissue types within an image patch according to a hierarchical histological taxonomy, identifying an image patch associated with normal tissue, generating a pixel-level segmented image patch for an image patch, generating an encoded image patch for an image patch of at least one tissue, searching for one or more histopathological images, and assigning an image patch to one or more pathological cases.

Abstract: Computer implemented methods and systems directed to a technological improvement in electronic data compression and transmission between two computer systems using semantic analysis are disclosed. The method includes the step of compressing, at a first computer, a plurality of queued artifacts based on one or more network decision variables. The compression includes prioritizing the queued artifacts. The compression further includes determining a first set of artifacts in a set of queued artifacts to transmit and a second set of artifacts in a set of queued artifacts to only send links. The compression further includes replacing unnecessary content in the set of queued artifacts with one or more identifiers. The method further includes the step of transmitting, from the first computer, one or more batches of the compressed data over a network to a second computer.

Abstract: The subject technology receives assessment values determined by a first machine learning model deployed on a client electronic device, the assessment values being indicative of classifications of input data and the assessment values being associated with constraint data that comprises a probability distribution of the assessment values with respect to the classifications of the input data. The subject technology applies the assessment values determined by the first machine learning model to a second machine learning model to determine the classifications of the input data. The subject technology determines whether accuracies of the classifications determined by the second machine learning model conform with the probability distribution for corresponding assessment values determined by the first machine learning model.

Abstract: A parameter server located at a base station may coordinate federated learning among multiple user equipment (UEs) using over-the-air (OTA) aggregation with power control to mitigate aggregation distortion due to amplitude misalignment. The parameter server may select a first group of UEs for a first OTA aggregation session of a federated learning round based on a common received power property of each UE in the first group of UEs. The parameter server may transmit a global model to the first group of UEs. Each UE in the first group may train the global model based on a local dataset and transmit values associated with the trained local model. The parameter server may receive, on resource elements for the first group of UEs, a first aggregate amplitude modulated analog signal representing a combined response from the first group of UEs.

Abstract: Embodiments of the disclosure provide a method for accelerating an asset execution in an electronic device. The method includes: detecting, by the electronic device, a user interface (UI) transition associated with a first application; predicting, by the electronic device, a sequence of at least one asset to be offloaded for a subsequent UI transition based on an asset parameter using a ML model, wherein the subsequent UI transition is associated with the first application or a second application; offloading, by the electronic device, the at least one asset in the sequence; and storing, by the electronic device, the at least one offloaded asset to a memory of the electronic device.

Abstract: The present application discloses a method, system, and computer system for building a model associated with a dataset. The method includes receiving a data set, the dataset comprising a plurality of keys and a plurality of key-value relationships, determining a plurality of models to build based at least in part on the dataset, wherein determining the plurality of models to build comprises using the dataset format information to identify the plurality of models, building the plurality of models, and optimizing at least one of the plurality of models.

Abstract: In an aspect, a system for using artificial intelligence to evaluate, correct, and monitor user attentiveness includes a forward-facing camera, the forward-facing camera configured to capture a video feed of a field of vision on a digital screen, at least a user alert mechanism configured to output a directional alert to a user, a processing unit in communication with the forward-facing camera and the at least a user alert mechanism, a screen location to spatial location map operating on the processing unit, and a motion detection analyzer operating on the processing unit, the motion detection analyzer designed and configured to detect, on the digital screen, a rapid parameter change, determine a screen location on the digital screen of the rapid parameter change, retrieve, from the screen location to spatial location map, a spatial location based on the screen location, and generate, using the spatial location, the directional alert.

Abstract: A method of training a learning network is described. The method includes generating a first estimate of a gradient for the learning network and generating subsequent estimates of the gradient using a feedback network. The feedback network generates improved perturbations for the subsequent gradient estimates. Gradient estimates include the first estimate of the gradient and the subsequent estimates of the gradient. The method also includes using the gradient estimates to determine weights in the learning network. The improved perturbations may include lower variance perturbations.

Abstract: A system and method generate recommendations with cold starts. The system comprises a hardware-based processor, a memory, and a set of modules. The memory stores item taxonomy data for at least one item, stores client descriptive data for at least one client, and stores historical response data for at least one item responded to by the at least one client. The set of modules includes a machine learning module and a recommendation module. The machine learning module generates a response probability matrix using the historical response data, the item taxonomy data, and the client descriptive data. The recommendation module generates and outputs a recommendation corresponding to input data using the information deduced in the response probability matrix. The method implements the system.

Abstract: Described herein are a system and techniques for detecting whether biometric data provided in an access request is genuine or a replay. In some embodiments, the system uses an machine learning model trained using genuine and replay sample data which is optimized in order to produce a result set in which results for the genuine samples are pulled closer to a genuine center and results for the replay samples are pushed away from the genuine center. Subjecting input biometric data (e.g., an audio sample) to the trained model results in a classification of the input biometric data as genuine or replay, which can then be used to determine whether or not to verify the input biometric data.

Abstract: There is disclosed a computer-implemented method for lossy image or video compression, transmission and decoding, the method including the steps of: (i) receiving an input image at a first computer system; (ii) encoding the input image using a first trained neural network, using the first computer system, to produce a latent representation; (iii) quantizing the latent representation using the first computer system to produce a quantized latent; (iv) entropy encoding the quantized latent into a bitstream, using the first computer system; (v) transmitting the bitstream to a second computer system; (vi) the second computer system entropy decoding the bitstream to produce the quantized latent; (vii) the second computer system using a second trained neural network to produce an output image from the quantized latent, wherein the output image is an approximation of the input image. Related computer-implemented methods, systems, computer-implemented training methods and computer program products are disclosed.

Abstract: Methods, systems and computer program products for determining recommended parameters for use in generating a word embedding model are provided. Aspects include storing a plurality of meaningful test cases. Each meaningful test case includes a test data profile and one or more test model parameters used to create a word embedding model that has been classified as yielding meaningful results. Aspects include receiving a production data set to be used in generating a new word embedding model. The production data set includes data stored in a relational database having a plurality of columns and a plurality of rows. Aspects include generating a data profile associated with the production data set. Aspects include generating a recommendation for one or more production model parameters for use in building a word embedding model based on the data profile associated with the production data set and the plurality of meaningful test cases.

Abstract: A heuristic engine includes capabilities to collect an unstructured data set, including document image data and correlate the image data with known valid data to detect document fraud. Notifications of fraud detection may include particular signature images, or characteristics of a document image. By feeding back indications of document fraud with correlations to past instances of fraud into the heuristic algorithm, the algorithm may learn and improve in fraud detection accuracy.

Abstract: An Integrated Virtual Patient Framework (IVPF) for providing decision support that evolves with increasing data collected on a given patient. Support decisions for patients with limited data is made using statistical prediction tools derived from historical trajectories of similar patients. As patient histories grow, decision support is provided by mathematical models that constrain the possible dynamics of the patient to more detailed predictive models. Weights for each model are assigned depending on uncertainties arising from data fitting and model properties. As new data are entered into a patient record, the models are recalibrated and the weights are adjusted, leading to updated decision support information. The framework also suggests the benefit of additional follow-up data collection events, optimizing the data collection as well as how the IVPF generates predictions. The framework also may present scenarios to patients in a way that informs them of treatment outcomes, given various strategies.

Abstract: The present disclosure provides new and innovative systems and methods for identifying computing devices. In an example, a computer-implemented method includes obtaining device attribute data for a computing device, generating a device fingerprint including a piecewise hash generated based on the device attribute data, determining a closest matching fingerprint, calculating attribute differences based on the device fingerprint and the closest matching fingerprint, verifying the closest matching fingerprint identifies the computing device based on the attribute differences, updating the closest matching fingerprint in a fingerprint database, and transmitting a notification generated based on the verifying.

Abstract: This application relates to employing trained machine learning processes to predict sales across various sale channels. For example, a computing device may generate features based on historical sales information, and trains the machine learning processes based on the generated features. In some examples, the computing device determines fixed cost effects from selling items across various sales channels, and adjusts the sales information based on the fixed cost effects. The computing device also generates features based on the adjusted sales. The computing device may apply the trained machine learning processes to sales information for one or more items to predict the sales of one or more items across one or more sales channels during a future temporal period. In some examples, the trained machine learning processes generate a ranking of items for a sales channel based on the output generated from the trained machine learning processes.

Abstract: In one embodiment, a recommendation service of a device provides a recommended action to a client of an online application predicted to improve a quality of experience metric for the online application. The device receives feedback from the client indicative of the recommended action not being implemented by a user of the client. The device determines, based on the feedback, a reason for the recommended action not being implemented. The device updates the recommendation service based on the reason for the recommended action not being implemented.

Abstract: Disclosed are systems, methods, and non-transitory media for performing passive radio frequency (RF) location detection operations. In some aspects, RF data, such as RF signals including channel state information (CSI), can be received from a wireless device. The RF data can be provided to a self-supervised machine-learning architecture that is configured to perform object location estimation.

Abstract: Methods, systems, and apparatuses for programmatically managing email data integration between an external email resource associated with a group-based communication system user and a group-based communication system are provided herein.

Abstract: Provided are a system and a method for prediction of an intradialytic adverse event, where a machine learning model of two-class classification is utilized to predict intradialytic adverse events in quasi-real time, such that features extracted in an ongoing hemodialysis process in real time can have the hemodialysis session alerted for forthcoming adverse events. Therefore, clinicians can be warned to take necessary actions and adjust the hemodialysis machine settings in advance. In addition, a computer readable medium thereof is also provided.

Abstract: A method includes monitoring, during a first time interval, traffic associated with one or more applications executed by a cluster of compute nodes and determining, in view of the traffic associated with the one or more applications during the first time interval, that the traffic is predicted to exceed a capacity threshold of the cluster of compute nodes at an end of a second time interval. The method further includes initiating startup of an additional compute node to be added to the cluster of compute nodes for executing replicas of the one or more applications.

Abstract: Reducing resource consumption of a database system and a machine learning (ML) system is described. Data is received from a ML application of a database system. The data includes a first inference call for a predicted response to the received data. The first inference call is a request to a ML model to generate one or more predictions for which a response is unknown. A ML model using the received data generates an output comprising the predicted response to the data. The output for future inference calls is cached in an inference cache so as to bypass the ML model. The generated output to the ML application is provided by the ML model. A second inference call is received which includes the data of the first inference call. The cached output is retrieved from the inference cache. The retrieving bypasses the ML model.

Abstract: A scenario presentation device presents, in an electronic display, selectable for possible activities. The device receives a selection of a first scenario option. The selected first scenario option corresponds to a selected activity that includes an action involving an item to be performed over a period of time. The device determines anticipated changes to the environment over the period of time. Using the anticipated changes to the environment over the period of time, a projected environment representation is determined for the selected activity. The projected environment representation includes one or more images depicting changes to the environment. The projected environment representation is presented in the electronic display.

Abstract: A computer-implemented method for lossy image or video compression, transmission and decoding, the method including the steps of: (i) receiving an input image at a first computer system; (ii) encoding the input image using a first trained neural network, using the first computer system, to produce a latent representation; (iii) quantizing the latent representation using the first computer system to produce a quantized latent; (iv) entropy encoding the quantized latent into a bitstream, using the first computer system; (v) transmitting the bitstream to a second computer system; (vi) the second computer system entropy decoding the bitstream to produce the quantized latent; (vii) the second computer system using a second trained neural network to produce an output image from the quantized latent, wherein the output image is an approximation of the input image. Related computer-implemented methods, systems, computer-implemented training methods and computer program products.

Abstract: A method and system analyze data in a database. The method and system include defining a plurality of set of rules, wherein each set of rules corresponds to a predictive model, storing the each set of rules corresponding to the predictive model in a library as a user-defined function, and calling the user-defined function via a standard sequel language.

Abstract: Duplicating identification in a graph having a second version. The graph includes nodes representing entities and edges representing relationships between the entities. The method includes: providing a previous first version of the graph. At least two target nodes of the graph may be identified. The first version and the second version of the graph may be compared for determining a comparison score indicative of a similarity between the two target nodes. The comparison score may be used for determining whether the two target nodes are duplicates with respect to each other.

Abstract: Systems and methods for monitoring suspicious communication network traffic. The methods include obtaining data associated with a sequence of communication events transmitted via the communication network and determining an entropy approximation measure associated at least one event attribute for the sequence of communication events. The method includes generating a threat prediction value based on an anomaly classification model and the entropy approximation measure. The anomaly classification model is trained based on prior sequences of communication events to identify a non-outlier anomaly range associated with the at least one event attribute. The threat prediction value is generated based on classification of the entropy approximation measure relative to the non-outlier anomaly range associated with the at least one attribute for identifying a potential threat. The method includes transmitting a signal for communicating that the sequence is a potential threat within the communication network.

Abstract: A system and method for performing tactical segmentation including a supply chain network having a tactical segmentation planner, an inventory system, a transportation network, supply chain entities and a computer.

Abstract: The invention relates to a QoX adaptive management-based context information uncertainty elimination system and a working method thereof. The system includes a sensor module, a context information acquisition and modeling module, a context threshold information preset module, an original context information detection module, an adaptive management module, an uncertainty elimination module, a context information correlation analysis module, an original context information flow reconstruction module, a composite context information flow module, a fusion and reasoning module, a context application layer adjustment module and a knowledge base.

Abstract: Systems, methods, and apparatuses for determining feature importance of analytics data in predicting a response value include receiving data records, each data record including a response value and values of features associated with the response value; splitting the data records into datasets, each dataset including a part of the data records; generating a machine learning model using each of the datasets, the machine learning model outputting one or more predicting features having influence in predicting the response value for each of the datasets; determining an important feature based on the one or more predicting features; and generating report data indicating that a business metric associated with the important feature has the highest predicted influence among the features on predicting the response value.