Abstract: A method provides learning with noisy labels. The method includes generating a first network of a machine learning model with a first set of parameter initial values, and generating a second network of the machine learning model with a second set of parameter initial values. First clean probabilities for samples in a training dataset are generated using the second network. A first labeled dataset and a first unlabeled dataset are generated from the training dataset based on the first clean probabilities. The first network is trained based on the first labeled dataset and first unlabeled dataset to update parameters of the first network.

Abstract: Provided is a method for implementing reinforcement learning by a neural network. The method may include performing, for each epoch of a first predetermined number of epochs, a second predetermined number of training iterations and a third predetermined number of testing iterations using a first neural network. The first neural network may include a first set of parameters, the training iterations may include a first set of hyperparameters, and the testing iterations may include a second set of hyperparameters. The testing iterations may be divided into segments, and each segment may include a fourth predetermined number of testing iterations. A first pattern may be determined based on at least one of the segments. At least one of the first set of hyperparameters or the second set of hyperparameters may be adjusted based on the pattern. A system and computer program product are also disclosed.

Abstract: A map fusing method includes receiving a source graph and a target graph. The source graph is representative of a source map and the target graph is representative of a target map and includes nodes and edges that connect the nodes. The method further includes processing each of the source graph and the target graph in a graph convolutional layer to provide graph convolutional layer outputs related to the source graph and to the target graph, processing each of the graph convolutional layer outputs for the source graph and the target graph in a linear rectifying layer to output node feature maps related to the source graph and the target graph. The method further includes selecting pairs of node representations from the node feature maps related to the source graph and the target graph and concatenating the selected pairs to output selected and concatenated pairs of node representations.

Abstract: The disclosure relates to a system and method of configuring and validating multi-vendor and multi-region Internet-of-Things (IoT) devices using reinforcement learning. In some embodiments, the method includes generating a matching table for each of a plurality of IoT sensors based on a plurality of sensor attributes extracted from a product data associated with an IoT sensor; acquiring an identification information and operational information associated with the IoT sensor and a set of neighboring IoT sensors for each of the plurality of IoT sensors; identifying an appropriate set of IoT sensors from the plurality of IoT sensors, based on a user requirement, the matching table, the identification information and the operational information, using a Reinforcement Learning (RL) model; and dynamically configuring each of the appropriate set of IoT sensors based on a vendor type.

Abstract: A portable electronic device is provided. The electronic device includes a transparent front glass cover including a planar portion that forms a front surface of the electronic device, a planar rear glass cover that forms a rear surface of the electronic device, a metal bezel that surrounds a space formed by the front glass cover and the rear glass cover, and a flexible display device that is embedded in the space and exposed through the front glass cover. The front cover includes a left bent portion and a right bent portion on the left and right of the planar portion at the center of the front cover.

Abstract: An apparatus including circuitry configured to determine a probability by combining at least: a probability that an event is present within a current feature of interest given a first set of previous features of interest, and a probability that the event is present within the current feature of interest given a second set of previous features of interest, different to the first set of previous features of interest; circuitry configured to detect the event based on the determined probability; and circuitry configured to control, in dependence on the detection of the event, performance of an action.

Abstract: Aspects of the present disclosure relate to processing irregularly arranged characters. An image is received. An irregularly arranged character within the image is detected. A direction of the irregularly arranged character is modified to a proper direction to obtain a properly oriented character. The properly oriented character is recognized to obtain a first identified character. The image is then rebuilt by replacing the irregularly arranged character with the first identified character, the first identified character in a machine-encoded format.

Abstract: Techniques are described for providing location-based information and functionality to people and computing devices in various ways. In at least some situations, the techniques include enabling multiple people in a common geographic area to interact in various ways, such as via devices capable of communications (e.g., cellular telephones, computing devices with wired and/or wireless communications capabilities, etc.), while in other situations at least some users who are remote from a particular geographic area may be allowed to intercommunicate with one or more other users or other entities in or related to that geographic area. In addition, the techniques include enabling the creation and maintenance of location-based virtual groups of users (also referred to as “clouds”), such as for users of mobile and/or fixed-location devices. Such clouds may enable various types of interactions between group members, and may be temporary and/or mobile.

Abstract: Techniques for providing audio services to multiple devices are described. For instance, connections between a hands-free unit and multiple wireless devices are established. The connections are themselves used to establish active communication channels, such as active audio communication channels, between the hands-free unit and the wireless devices, such as during a phone call. Upon establishment of an active communication channel with one of the wireless devices, the connections to the other wireless devices are disconnected—and/or additional connections refused—for the duration of the active communication channel. Furthermore, a routing module in various embodiments permits multiple hands-free units to route active communication channels to each other depending on user location.

Abstract: A computer system trains a neural network on an instance segmentation task by casting the problem as one of mapping each pixel to a probability distribution over arbitrary instance labels. This simplifies both the training and inference problems, because the formulation is end-to-end trainable and requires no post-processing to extract maximum a posteriori estimates of the instance labels.

Abstract: Systems and methods are described in relation to specific technical improvements adapted for machine learning architectures that conduct classification on numerical and/or unstructured data. In an embodiment, two neural networks are utilized in concert to generate output data sets representative of predicted future states of an entity. A second learning architecture is trained to cluster prior entities based on characteristics converted into the form of features and event occurrence such that a boundary function can be established between the clusters to form a decision boundary between decision regions. These outputs are mapped to a space defined by the boundary function, such that the mapping can be used to determine whether a future state event is likely to occur at a particular time in the future.

Abstract: An electronic apparatus and method for heatmap visualization of object detections is provided. The electronic apparatus inputs an image frame including an object of interest to Deep Neural Network (DNN) model and extracts an object detection result associated with the object of interest as output of the DNN model for the input image frame. The object detection result includes bounding box coordinates for the object of interest. The electronic apparatus segments the input image frame into a plurality of image portions based on the bounding box coordinates and determines, for each of the plurality of image portions, a weight value indicative of a likelihood that a corresponding image portion belongs to the object of interest. The electronic apparatus generates, based on the determined weight value, a visualization frame which includes heatmap visualization of a region that is included in the image frame and is bounded by the bounding box coordinates.

Abstract: A wearable device that communicates with a host device can be used to initiate a communication functionality of the host device (e.g., telephone calls, text messages). The wearable device can obtain user input indicating a recipient of the communication and in some instances content for the communication and can provide an instruction to the host device. The host device can use the indicated recipient and content to initiate communication and where applicable to send the content. Recipients and/or content can be selected from predefined lists available on the wearable device.

Abstract: Information about a drug-containing vessel is determined by capturing image data of the curved surface of a cylindrical portion of a drug-containing vessel. The image data is unfurled from around the curved surface, binarised, and a template matching algorithm employed to determine that the label information comprises candidate information about the vessel and/or the drug.

Abstract: Computational algorithms integrate and analyze data to consider multiple interdependent, heterogeneous sources and forms of patient data, and using a classification model, provide new learning paradigms, including privileged learning and learning with uncertain clinical data, to determine patient status for conditions such as acute respiratory distress syndrome (ARDS) or non-ARDS.

Abstract: One or more multi-stage optimization iterations are performed with respect to a compression algorithm. A given iteration comprises a first stage in which hyper-parameters of a perceptual quality algorithm are tuned independently of the compression algorithm. A second stage of the iteration comprises tuning hyper-parameters of the compression algorithm using a set of perceptual quality scores generated by the tuned perceptual quality algorithm. The final stage of the iteration comprises performing a compression quality evaluation test on the tuned compression algorithm.

Abstract: Disclosed is an artificial intelligence (AI)-based self-control air conditioner. The AI-based self-control air conditioner includes a communication unit configured to receive an image including member data for identifying the member from an image acquisition apparatus corresponding to a group including at least one member, and a processor configured to recognize the member data from the received image, to acquire operation data including an operation condition of an air conditioner, which is desired by the member, based on the recognized data, to store member information including the member data and the operation data in a database, and to acquire and analyze the operation condition of the air conditioner, which is desired by the member, with respect to at least one member from a plurality of pieces of member information corresponding to the group stored in the database, wherein the air conditioner is autonomously driven according to control of the processor.

Abstract: A method for identifying a logo within at least one image includes identifying an area containing the logo within the at least one image, extracting logo features from the area by analyzing image gradient vectors associated with the at least one image, and using a machine learning model to identify the logo from the extracted logo features, wherein the machine learning model is trained to identify at least one target logo based on a received image data containing the logo features.

Abstract: A substrate inspection method in a substrate treatment system including a plurality of treatment apparatuses each performing a predetermined treatment on a substrate, includes: imaging a surface of a substrate before being treated in the treatment apparatuses to acquire a first substrate image; extracting a predetermined feature amount from the first substrate image; selecting an inspection recipe corresponding to the feature amount extracted from the first substrate image, from a storage unit in which a plurality of inspection recipes each set corresponding to the feature amount in a different range are stored; imaging the surface of the substrate after being treated in the treatment apparatuses to acquire a second substrate image; and determining presence or absence of a defect of the substrate, based on the selected inspection recipe and the second substrate image.

Abstract: Disclosed are an image processing method and apparatus, an electronic device and a computer-readable storage medium. The method comprises: acquiring a video image; when a preset target is detected in the video image, superimposing a foreground sticker on a target image corresponding to the preset target; and when a preset action of the preset target in the video image is detected, generating a screen special effect, in the embodiments of the present disclosure, a video image is acquired, when a preset target is detected in the video image, a foreground sticker is superimposed on a target image corresponding to the preset target, and when a preset action of the preset target in the video image is detected, a screen special effect is generated, such that a screen special effect for the preset action of the preset target can be realized.