Abstract: An image differentiation system receives input feature vectors for multiple input images and reference feature vectors for multiple reference images. In some cases, the feature vectors are extracted by an image feature extraction module trained based on training image triplets. A differentiability scoring module determines a differentiability score for each input image based on a distance between the input feature vectors and the reference feature vectors. The distance for each reference feature vector is modified by a weighting factor based on interaction metrics associated with the corresponding reference image. In some cases, an input image is identified as a differentiated image based on the corresponding differentiability score. Additionally or alternatively, an image modification module determines an image modification that increases the differentiability score of the input image. The image modification module generates a recommended image by applying the image modification to the input image.

Abstract: A unique implementation of a machine learning application for suggesting actions for a user to undertake is described herein. The application transforms a history of user behavior for a plurality of users into a set of models that represent user actions, and the optimal actions, given a set of parameters. These models are then used to suggest that users in a payments or banking environment take certain actions based on a best in class model derived from the best performing user. The models are created using the DensiCube, random forest, K-means or other machine learning algorithms.

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 computing system for detecting a pattern of fraudulent network events in a payment card network is configured to continuously receive a plurality of scored transaction authorization requests each including a respective account number and a respective fraud score. The computing system is also configured to sort the scored transaction authorization requests into account ranges based the account number, and sort the transaction authorization requests within each of the account ranges into a fraud score range stripes based on the corresponding fraud score. The computing system is further configured to calculate, for the scored transaction authorization requests within each fraud score range stripe, a ratio of a cumulative metric for a shorter time period over a longer time period, and detect, in near real-time, a fraud event associated with one of the account ranges based on the ratio for one of the fraud score range stripes within the account range.

Abstract: Disclosed is a beamforming method using a deep neural network. The deep neural network may include an input layer, L hidden layers, and an output layer, and the beamforming method may include: obtaining channel information h between a base station and K terminals and a transmit power limit value P of the base station, and inputting h and P into the input layer; and performing beamforming on signals to be transmitted to the K terminals using beamforming vectors derived using the output layer and at least one activation function, wherein the base station transmits the signals to the K terminals using M transmit antennas. Here, the output layer may be configured in a direct beamforming learning (DBL) scheme, a feature learning (FL) scheme, or a simplified feature learning (SFL) scheme.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate quantum topological classification are described. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a topological component that employs one or more quantum computing operations to identify one or more persistent homology features of a topological simplicial structure. The computer executable components can further comprise a topological classifier component that employs one or more machine learning models to classify the topological simplicial structure based on the one or more persistent homology features.

Abstract: A student neural network may be trained by a computer-implemented method, including: inputting common input data to each teacher neural network among a plurality of teacher neural networks to obtain a soft label output among a plurality of soft label outputs from each teacher neural network among the plurality of teacher neural networks, and training a student neural network with the input data and the plurality of soft label outputs.

Abstract: A method for using distributed representations of data items within a first set of data documents clustered in a first two-dimensional metric space to generate a cluster of distributed representations in a second two-dimensional metric space includes clustering in a first two-dimensional metric space, by a reference map generator, a set of data documents, generating a semantic map. A parser generates an enumeration of data items occurring in the set of data documents. A representation generator generates a distributed representation using occurrence information about each data item. A sparsifying module receives an identification of a maximum level of sparsity and reduces a total number of set bits within the distributed representation. The reference map generator clusters, in a second two-dimensional metric space, a set of SDRs retrieved from the SDR database and selected according to a second at least one criterion, generating a second semantic map.

Abstract: Embodiments of the present disclosure provide a method and apparatus for processing an image, and relates to the field of computer vision technology. The method may include: acquiring a value to be processed, where the value to be processed is associated with an image to be processed; and processing the value to be processed by using a quality scoring model to generate a score of the image to be processed in a target scoring domain, where the score of the image to be processed in the target scoring domain is related to an image quality of the image to be processed.

Abstract: A service action category based cloud security system and method implement cloud security by categorizing service actions of cloud service providers into a set of service action categories. The service action categorization is performed agnostic to the applications or functions provided by the cloud service providers and also agnostic to the cloud service providers. With the service actions of cloud service providers thus categorized, cloud security monitoring and threat detection can be performed based on service action categories. Thus, cloud security can be implemented without requiring knowledge of the applications supported by the cloud service providers and without knowing all of the individual service actions supported by the cloud service providers.

Abstract: A reference map generator clusters, into a semantic map, a set of data documents selected according to at least one criterion and associated with a medical diagnosis. A parser generates an enumeration of measurements occurring in the set of data documents. A representation generator generates for each measurement in the enumeration, a sparse distributed representation (SDR). The method includes storing, by a processor on a second computing device, in each of a plurality of memory cells on the second computing device, one of the generated SDRs. A diagnosis support module receives a document comprising a plurality of measurements. The representation generator generates a compound SDR for the document. Each of the plurality of bitwise comparison circuits determine a level of overlap between the compound SDR and the stored generated SDR. The diagnosis support module provides an identification of the medical diagnosis associated with a stored SDR.

Abstract: Systems and methods of determining file-access patterns in at least one computer network, the network comprising a file-access server, including training a first machine learning (ML) algorithm with a first training dataset comprising vectors representing network traffic such that the first ML algorithm learns to determine network characteristics associated with file-access traffic, determining, using the first ML algorithm, network characteristics based on highest interaction of traffic with the file-access server compared to other interactions in the at least one computer network, and determining file-access patterns in the at least one computer network based on the network characteristics associated with file-access traffic.

Abstract: A mechanism is described for facilitating misuse index for explainable artificial intelligence in computing environments, according to one embodiment. A method of embodiments, as described herein, includes mapping training data with inference uses in a machine learning environment, where the training data is used for training a machine learning model. The method may further include detecting, based on one or more policy/parameter thresholds, one or more discrepancies between the training data and the inference uses, classifying the one or more discrepancies as one or more misuses, and creating a misuse index listing the one or more misuses.

Abstract: Embodiments described herein provide a technique to crowdsource labeling of training data for a machine learning model while maintaining the privacy of the data provided by crowdsourcing participants. Client devices can be used to generate proposed labels for a unit of data to be used in a training dataset. One or more privacy mechanisms are used to protect user data when transmitting the data to a server. The server can aggregate the proposed labels and use the most frequently proposed labels for an element as the label for the element when generating training data for the machine learning model. The machine learning model is then trained using the crowdsourced labels to improve the accuracy of the model.

Abstract: There is provided a system and a method of generating an annotated structured dataset, comprising: receiving a medical classification term, searching over the unstructured patient data for extracting unclassified unstructured text fragments, presenting a subset of the unclassified unstructured text fragments, receiving an indication of a selection of none or at least one of the text fragments, and one of: (i) classifying non-selected unclassified unstructured text fragments according to the medical classification term, and classifying selected text fragments as not satisfying the medical classification term, and (ii) classifying selected unclassified unstructured text fragments according to the medical classification term, and classifying non-selected unclassified unstructured text fragments as not satisfying the medical classification term, and iterating the searching, and/or the presenting, until no text fragments are obtained by the search, wherein the annotated structured dataset is created by the classif

Abstract: A method and system is provided for identifying patterns in datasets by identifying delimited regions of feature-space in which patterns occur. The delimited regions are then combined into an ensemble able to make predictions based on the identified regions of feature-space. The method may be used for classification, for regression, for auto-encoding, for simulation, and for other applications of pattern detection.

Abstract: Combining predictions made by multiple different prediction systems, including: obtaining a new input sample; obtaining a combiner which comprises optimal selection values that are configured to maximize a predefined performance measure; automatically applying multiple different prediction systems to the new input sample, to generate predictions; and automatically selectively combining the generated predictions based on the optimal selection values, to generate a combined prediction whose predefined performance measure is improved compared to individual usage of each of the prediction systems.

Abstract: A method and a system for training a machine learning algorithm (MLA) for object classification. The machine learning algorithm includes an embedding layer and a classification layer. A set of embedding indices representing a reference object is received. The set of embedding indices has been generated based on a byte representation of the reference object. A label associated with the reference object indicative of a reference class the objects belongs to is received. The MLA is iteratively trained to classify objects by embedding the set of embedding indices to obtain an input vector and by predicting an estimated class based on the input vector, and updating a parameter of at least one of the embedding layer and the updated embedding layer. The set of embedding indices is generated by parsing the byte representation to obtain byte n-grams and by applying a hash function on the byte n-grams.

Abstract: In an embodiment, a list of domains is received that includes one or more categories for each domain. The categories are assigned to each domain using a classifier that is trained using features extracted from webpages known to be associated with particular categories. An administrator creates access rules for users, or groups of users, that control the categories of domains that each user is permitted to access or not access. When a user makes a request for a webpage, access rules associated with the user are retrieved, and one or more categories associated with the domain of the requested webpage are determined using the list of domains. If any of the one or more categories of the domain violate an access rule associated with the user, the request for the webpage is denied. Otherwise the user is allowed to access the webpage.

Abstract: Methods, systems, apparatuses, and computer-readable storage mediums are described for machine learning-based techniques for reducing the visual complexity of a dependency graph that is representative of an application or service. For example, the dependency graph is generated that comprises a plurality of nodes and edges. Each node represents a compute resource (e.g., a microservice) of the application or service. Each edge represents a dependency between nodes coupled thereto. A machine learning-based classification model analyzes each of the nodes to determine a likelihood that each of the nodes is a problematic compute resource. For instance, the classification model may output a score indicative of the likelihood that a particular compute resource is problematic. The nodes and/or edges having a score that exceed a predetermined threshold are provided focus via the dependency graph.

Abstract: The present disclosure provides a computation device and method. The device may include an input module configured to acquire input data; a model generation module configured to construct an offline model according to an input network structure and weight data; a neural network operation module configured to generate a computation instruction based on the offline model and cache the computation instruction, and compute the data to be processed based on the computation instruction to obtain a computation result; and an output module configured to output a computation result. The device and method may avoid the overhead caused by running an entire software architecture, which is a problem in a traditional method.

Abstract: A method that may include training a student ODNN to mimic a teacher ODNN. The training may include calculating a teacher student detection loss that is based on a pre-bounding-box output of the teacher ODNN. The pre-bounding-box output of the teacher ODNN is a function of pre-bounding-box outputs of different ODNNs that belong to the teacher ODNN. The method may also include detecting one or more objects in an image, by feeding the image to the trained student ODNN; outputting by the trained student ODNN a student pre-bounding-box output; and calculating one or more bounding boxes based on the student pre-bounding-box output.

Abstract: An image processing method includes a first step of acquiring input data including a captured image and optical system information relating to a state of an optical system used for capturing the captured image and a second step of inputting the input data to a machine learning model and of generating an estimated image acquired by sharpening the captured image or by reshaping blurs included in the captured image.

Abstract: A surgical instrument navigation system is provided that visually simulates a virtual volumetric scene of a body cavity of a patient from a point of view of a surgical instrument residing in the cavity of the patient. The surgical instrument navigation system includes: a surgical instrument; an imaging device which is operable to capture scan data representative of an internal region of interest within a given patient; a tracking subsystem that employs electro-magnetic sensing to capture in real-time position data indicative of the position of the surgical instrument; a data processor which is operable to render a volumetric, perspective image of the internal region of interest from a point of view of the surgical instrument; and a display which is operable to display the volumetric perspective image of the patient.

Abstract: Systems and methods for aggregating data. The system is configured to receive metadata from an interactive graphical user interface (GUI) of a user device, aggregate field values from the data stored on one or more databases based on the received metadata and generate filter instructions based on the received metadata. The system is further configured to transmit the aggregated field values and the filter instructions to the user device, receive a user-customized filter set and subscription request for a synthetic symbol associated with the user-customized filter set from the user device, and create the synthetic symbol responsive to the subscription request. Moreover, the system aggregates one or more data values from the data stored on the databases associated with the created synthetic symbol and generates instructions to display the data values on the interactive GUI in accordance with the user-customized filter set associated with the created synthetic symbol.

Abstract: Techniques and apparatuses are described for machine-learning architectures for simultaneous connection to multiple carriers. In implementations, a network entity determines at least one deep neural network (DNN) configuration for processing information exchanged with a user equipment (UE) over a wireless communication system using carrier aggregation that includes at least a first component carrier and a second component carrier. At times, the at least one DNN configuration includes a first portion for forming a first DNN at the network entity, and a second portion for forming a second DNN at the UE. The network entity forms the first DNN based on the first portion and communicates an indication of the second portion to the UE. The network entity directs the UE to form the second DNN based on the second portion, and uses the first DNN to exchange, over the wireless communication system, the information with the UE using the carrier aggregation.

Abstract: Disclosed is a system for generating personalized recommendations based on dynamic and customized content selections and modeling of the content selections. The system may receive a request with an identifier and a query, and may obtain a particular recommendation configuration based the identifier and the query. The system may retrieve a set of content that satisfies the query and that is identified with at least one content prioritization parameter specified in the particular recommendation configuration, may generate a set of models of one or more model types that model relevance between the set of content and a different event specified in the particular recommendation configuration, and may compute a score for each content in each model based on the modeled relevance. The system may present recommended content in a different order than the set of content based on aggregate scores compiled for each content from the set of models.

Abstract: An inference system trains and performs inference using a sparse neural network. The sparse neural network may include one or more layers, and each layer may be associated with a set of sparse weights that represent sparse connections between nodes of a layer and nodes of a previous layer. A layer output may be generated by applying the set of sparse weights associated with the layer to the layer output of a previous layer. Moreover, the one or more layers of the sparse neural network may generate sparse layer outputs. By using sparse representations of weights and layer outputs, robustness and stability of the neural network can be significantly improved, while maintaining competitive accuracy.

Abstract: A system and method for collecting and processing sensor data for facilitating and/or enabling autonomous, semi-autonomous, and remote operation of a vehicle, including: collecting surroundings at one or more sensors, and determining properties of the surroundings of the vehicle and/or the behavior of the vehicle based on the surroundings data at a computing system.

Abstract: A method for training a machine learning model, e.g., a neural network, using a regularization scheme is disclosed. The method includes generating regularized partial gradients of losses computed using an objective function for training the machine learning model.

Abstract: A learning method executed by a computer, the learning method including augmenting original training data based on non-stored target information included in the original training data to generate a plurality of augmented training data, generating a plurality of intermediate feature values by inputting the plurality of augmented training data to a learning model, and learning a parameter of the learning model such that, with regard to the plurality of intermediate feature values, each of the plurality of intermediate feature values generated from a plurality of augmented training data, augmented from reference training data, becomes similar to a reference feature value.

Abstract: A data processing system digitally processes data feeds of inhaler device operation. The data feed represents operation of an inhaler device. The system indexes the live data feed with a key value representing the inhaler device for which the live data feed is obtained. For a particular key value indexed in the in-memory data storage, the system queries, a data feed representing physical operation of an inhaler device, segments the live data feed for that particular key value into a plurality of data samples, process at least a portion of the data samples to classify each of the processed data samples; outputs a prompt specifying whether operation of the inhaler device is within a threshold range of operation. Audio data, temperature data, image data, and ranging data can be processed to classify operation of the inhaler device and the order of operations of the inhaler device.

Abstract: A process for training and sharing generic functional modules across multiple diverse (architecture, task) pairs for solving multiple diverse problems is described. The process is based on decomposing the general multi-task learning problem into several fine-grained and equally-sized subproblems, or pseudo-tasks. Training a set of (architecture, task) pairs then corresponds to solving a set of related pseudo-tasks, whose relationships can be exploited by shared functional modules. An efficient search algorithm is introduced for optimizing the mapping between pseudo-tasks and the modules that solve them, while simultaneously training the modules themselves.

Abstract: Apparatus, device, methods and system relating to a vehicular telemetry environment for monitoring vehicle components and providing indications towards the condition of the vehicle components and providing optimal indications towards replacement or maintenance of vehicle components before vehicle component failure.

Abstract: Tracking a current and/or previous position, velocity, acceleration, and/or heading of an object using sensor data may comprise determining whether to associate a current object detection generated from recently received (e.g., current) sensor data with a previous object detection generated from formerly received sensor data. In other words, a track may identify that an object detected in former sensor data is the same object detected in current sensor data. However, multiple types of sensor data may be used to detect objects and some objects may not be detected by different sensor types or may be detected differently, which may confound attempts to track an object. An ML model may be trained to receive outputs associated with different sensor types and/or a track associated with an object, and determine a data structure comprising a region of interest, object classification, and/or a pose associated with the object.

Abstract: A multi-layer technology stack includes a sensor layer including image sensors, a device layer, and a cloud layer, with interfaces between the layers. A method to curate different custom workflows for multiple applications include the following. Requirements for custom sets of data packages for the applications is received. The custom set of data packages include sensor data packages (e.g., SceneData) and contextual metadata packages that contextualize the sensor data packages (e.g., SceneMarks). Based on the received requirements and capabilities of components in the technology stack, the custom workflow for that application is deployed. This includes a selection, configuration and linking of components from the technology stack. The custom workflow is implemented in the components of the technology stack by transmitting workflow control packages directly and/or indirectly via the interfaces to the different layers.

Abstract: The present disclosure provides systems and methods that learn a loss function that, when (approximately) minimized over the training data, produces a model that performs well on test data according to some error metric. The error metric need not be differentiable and may be only loosely related to the loss function. In particular, the present disclosure presents a convex-programming-based algorithm that takes as input observed data from training a small number of models and produces as output a loss function. This algorithm can be used to tune loss function hyperparameters and/or to adjust the loss function on-the-fly during training.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed that optimize workflows. An example apparatus includes an intent determiner to determine an objective of a user input, the objective indicating a task to be executed in an infrastructure, a configuration composer to compose a plurality of workflows based on the determined objective, a model executor to execute a machine learning model to create a confidence score relating to the plurality of workflows, and a workflow selector to select at least one of the plurality of workflows for execution in the infrastructure, the selection of the at least one of the plurality of workflows based on the confidence score.

Abstract: Methods, systems, and computer program products for analyzing one or more perceived or technical problems or proposed solutions, and proposing a result are disclosed. In accordance therewith, a query is received as an input, one or more documents that are most closely semantically related to the query are retrieved, a set of concept terms derived from each of the query and the retrieved semantically related documents is obtained, a list of generic Solution Prompts, each of which generic Solution Prompt thereof includes a placeholder for insertion of a word or phrase from the set of concept terms, is provided, and a morphological analysis is applied to combine the list of generic Solution Prompts with the obtained set of concept terms to create a list of Specific Solution Prompts.

Abstract: A workflow support apparatus includes a classification section that classifies a document included in an original document from image data acquired by reading the original document, and a workflow searching section that searches for a workflow to which the document is to be attached, from the document classified by the classification section.

Abstract: Techniques are disclosed that enable automating user interface input by generating a sequence of actions to perform a task utilizing a multi-agent reinforcement learning framework. Various implementations process an intent associated with received user interface input using a holistic reinforcement policy network to select a software reinforcement learning policy network. The sequence of actions can be generated by processing the intent, as well as a sequence of software client state data, using the selected software reinforcement learning policy network. The sequence of actions are utilized to control the software client corresponding to the selected software reinforcement learning policy network.

Abstract: A search point determining method in an estimation process of a function, executed by a processor included in a search point determining apparatus, the method includes, calculating a search prediction time and a confidence interval upper limit obtained by using a Gaussian process for the function in each search candidate point from a past search result of the function, generating an area in a parameter space for each search candidate point by using a position of a search point close to the relevant search candidate point in a past search result, a search prediction time corresponding to each search candidate point, and a confidence interval upper limit corresponding to each search candidate point, and determining a search point based on a size of the area in a plurality of parameter spaces.

Abstract: Rule induction is used to produce human readable descriptions of patterns within a dataset. A rule induction algorithm or classifier is a type supervised machine learning classification algorithm. A rule induction classifier is trained, which involves using labelled examples in the dataset to produce a set of rules. Rather than using the rules/classifier to make predictions on new unlabeled samples, the training of the rule induction model outputs human-readable descriptions of patterns (rules) within the dataset that gave rise to the rules (rather than using the rules to predict new unlabeled samples). Parameters of the rule induction algorithm are tuned to favor simple and understandable rules, instead of only tuning for predictive accuracy. The learned set of rules are outputted during the training process in a human-friendly format.

Abstract: A method for operating a distributed neural network having a plurality of intelligent devices and a server includes: generating, by a first intelligent device of the plurality of intelligent devices, a first output using a first neural network model running on the first intelligent device and using a first input vector to the first neural network model; outputting, by the first intelligent device, the first output; receiving, by the first intelligent device, a gesture feedback on the first output from a user; determining, by the first intelligent device, a user rating of the first output from the gesture feedback; labeling, by the first intelligent device, the first input vector with a first label in accordance with the user rating; and training, by the first intelligent device, the first neural network model using the first input vector and the first label.

Abstract: An information processing apparatus includes an itemized reliability level calculation unit configured to calculate a first reliability level, wherein the first reliability level is a reliability level of classification target data, and a second reliability level, wherein the second reliability level is a reliability level of a label associated with the classification target data, a learning data reliability level calculation unit configured to calculate a learning data reliability level of learning data including the classification target data and the label based on the first reliability level and the second reliability level, and a classification model learning unit configured to formulate a classification model for giving a label to desired classification target data based on plural pieces of learning data and learning data reliability levels.

Abstract: We describe systems and methods for generating and training convolutional neural networks using biological sequences and relevance scores derived from structural, biochemical, population and evolutionary data. The convolutional neural networks take as input biological sequences and additional information and output molecular phenotypes. Biological sequences may include DNA, RNA and protein sequences. Molecular phenotypes may include protein-DNA interactions, protein-RNA interactions, protein-protein interactions, splicing patterns, polyadenylation patterns, and microRNA-RNA interactions, which may be described using numerical, categorical or ordinal attributes. Intermediate layers of the convolutional neural networks are weighted using relevance score sequences, for example, conservation tracks.

Abstract: Methods, systems, and computer program products for active explanation guided learning are provided herein. A computer-implemented method includes identifying a subset of training examples, from a set of training examples, based on at least one of (i) an uncertainty metric computed for each one of the training examples and (ii) an influence metric computed for each one of the training examples; outputting said subset of training examples to a user; obtaining, from the user, a user explanation for each training example in said subset of training examples, wherein each of the user explanations identifies at least one part of the corresponding training example; and training a machine learning model based at least in part on the user explanations, wherein said training comprises prioritizing the identified parts of the training examples in the subset.

Abstract: A first sample acquisition unit acquires a parameter sample from a prior distribution. A function execution unit acquires data from a distribution by supplying the sample to a function. A degree-of-similarity calculation unit calculates the degree of similarity between the data and correct data using a kernel function. A kernel mean construction unit constructs a kernel mean of a posterior distribution from the degree of similarity, the sample, and the kernel function. A second sample acquisition unit acquires a new parameter sample from the kernel mean and the kernel function. A sample evaluation unit determines whether the difference between new data obtained by supplying one sample selected from the new samples to the function and the correct data is less than a prescribed threshold value. When it is determined that the difference is less than the prescribed threshold value, the sample evaluation unit estimates the selected sample as a parameter.

Abstract: Method(s) and apparatus are provided for interfacing with a nervous system of a subject.

Abstract: Systems and methods for image recognition are provided. A style-transfer neural network is trained for each real image to obtain a trained style-transfer neural network. The texture or style features of the real images are transferred, via the trained style-transfer neural network, to a target image to generate styled images which are used for training an image-recognition machine learning model (e.g., a neural network). In some cases, the real images are clustered and representative style images are selected from the clusters.