Abstract: Systems and methods are disclosed for triggering an update to a machine-learning model upon detecting that a distribution of particular (e.g., recently collected) input data set is sufficiently different from a distribution training input data set used to train the model. The distributions may be determined to be sufficiently different when a classifier can identify to which distribution individual data elements belong (e.g., to at least a predetermined degree). An update to the machine-learning model can include morphing weights used by the model and/or retraining the model.

Abstract: A computer-implemented method for transferring data is provided. In an illustrative embodiment, the method includes retrieving, by a computer, an original dataset to be sent from a sender to a receiver. The method also includes generating, by the computer, a model based on at least a subset of the original dataset. The model generates a predicted dataset. The model is selected from a plurality of model types based on data complexity of the original dataset and a desired level of approximation of the predicted dataset to the original dataset. The method also includes transferring, by the computer, the model to the receiver. The receiver uses the model to generate the predicted dataset, wherein the predicted dataset matches the original dataset to a selected degree of approximation. Transfer of the model is quicker than transfer of the original dataset.

Abstract: One embodiment provides a method comprising receiving training data and experts' intuition, training a machine learning model based on the training data, predicting a class label for a new data input based on the machine learning model, estimating a degree of similarity of a target attribute of the new data input relative to the training data, and selectively applying a correction to the class label for the new data input based on the degree of similarity prior to providing the class label as an output. The target attribute is an attribute related to the experts' intuition.

Abstract: A method for utilizing human recognition and a method utilizing the same are provided. The method for utilizing human recognition includes updating a moving image database to include information about a moving image in which a cluster subject appears, the information being extracted based on clustering using a face feature; receiving a search condition; and detecting moving image information using the database. According to the present disclosure, a skeleton can be analyzed and a face can be recognized using an artificial intelligence (AI) model performing deep learning through a fifth generation (5G) network, and using the analysis result, a photographing composition can be determined, and moving image information can be constructed at an edge.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for channel-wise autoregressive entropy models. In one aspect, a method includes processing data using a first encoder neural network to generate a latent representation of the data. The latent representation of data is processed by a quantizer and a second encoder neural network to generate a quantized latent representation of data and a latent representation of an entropy model. The latent representation of data is further processed into a plurality of slices of quantized latent representations of data wherein the slices are arranged in an ordinal sequence. A hyperprior processing network generates a hyperprior parameters and a compressed representation of the hyperprior parameters. For each slice, a corresponding compressed representation is generated using a corresponding slice processing network wherein a combination of the compressed representations form a compressed representation of the data.

Abstract: The embodiments disclose a method including fabricating a one section foldable phone case for coupling with a foldable phone configured to fold from top to bottom, fabricating a one section foldable phone case for coupling with a foldable phone configured to fold from side to side, fabricating a two-section foldable phone case for coupling with a foldable phone configured to fold from top to bottom, fabricating a two-section foldable phone case for coupling with a foldable phone configured to fold from side to side, wherein phone cases are configured to view front and back foldable phone folded and unfolded screens, and embedding a RFID chip with a unique ID number into a foldable phone cases configured for locating and identifying a user's foldable phone case.

Abstract: Machine learning systems and associated methods are provided. A processor comprising at least one neural network can process a captured input image to translate the captured input image into an interactive demonstration presentation for an envisioned software product. The processing can include: automatically recognizing features within the captured input image; extracting the recognized features from the captured input image at the machine learning processor; processing each of the extracted features to determine a corresponding element in a library trained via a machine learning algorithm; and automatically replacing the extracted features from the captured input image with the one or more corresponding files or components to transform the captured input image into the interactive demonstration presentation.

Abstract: In various examples, historical trajectory information of objects in an environment may be tracked by an ego-vehicle and encoded into a state feature. The encoded state features for each of the objects observed by the ego-vehicle may be used—e.g., by a bi-directional long short-term memory (LSTM) network—to encode a spatial feature. The encoded spatial feature and the encoded state feature for an object may be used to predict lateral and/or longitudinal maneuvers for the object, and the combination of this information may be used to determine future locations of the object. The future locations may be used by the ego-vehicle to determine a path through the environment, or may be used by a simulation system to control virtual objects—according to trajectories determined from the future locations—through a simulation environment.

Abstract: Aspects relate to reconstructing phase images from brightfield images at multiple focal planes using machine learning techniques. A machine learning model may be trained using a training data set comprised of matched sets of images, each matched set of images comprising a plurality of brightfield images at different focal planes and, optionally, a corresponding ground truth phase image. An initial training data set may include images selected based on image views of a specimen that are substantially free of undesired visual artifacts such as dust. The brightfield images of the training data set can then be modified based on simulating at least one visual artifact, generating an enhanced training data set for use in training the model. Output of the machine learning model may be compared to the ground truth phase images to train the model. The trained model may be used to generate phase images from input data sets.

Abstract: An object detection device and an object detection method based on a neural network are provided. The object detection method includes: receiving an input image and identifying an object in the input image according to an improved YOLO-V2 neural network. The improved YOLO-V2 neural network includes a residual block, a third convolution layer, and a fourth convolution layer. A first input of the residual block is connected to a first convolution layer of the improved YOLO-V2 neural network, and an output of the residual block is connected to a second convolution layer of the improved YOLO-V2 neural network. Here, the residual block is configured to transmit, to the second convolution layer, a summation result corresponding to the first convolution layer. The third convolution layer and the fourth convolution layer are generated by decomposing a convolution layer of an original YOLO-V2 neural network.

Abstract: Provided is a learning method, a learning program, a learning device, and a learning system, for training a classification model, to further raise the correct answer rate of classification by the classification model. The learning method includes execution of generating one piece of composite data by compositing a plurality of pieces of training data of which classification has each been set, or a plurality of pieces of converted data obtained by converting the plurality of pieces of training data, at a predetermined ratio, inputting one or a plurality of pieces of the composite data into the classification model, and updating a parameter of the classification model so that classification of the plurality of pieces of training data included in the composite data is replicated at the predetermined ratio by output of the classification model, by a computer provided with at least one hardware processor and at least one memory.

Abstract: A method of operating a network comprising an edge node and a server. The method comprises obtaining, by the edge node, a plurality of data samples, determining, by the edge node, a plurality of output labels by applying a first machine learning model using an input memory having a first input memory size to the plurality of data samples, calculating, by the edge node, an error term based on the confidence score of a first output label from the plurality of output labels, determining, by the edge node, based on the error term, whether to modify the first input memory size of the machine learning model and, if so, generating a second machine learning model based on the first machine learning model and a second input memory size.

Abstract: A mobile phone holder that mounts a mobile phone on an appendage such as a limb of a user, an arm of a chair, and the like is disclosed. The mobile phone holder comprises of a cradle having a first arm and a second arm; an elongated member; and a supporter having a first curved member and a second curved member.

Abstract: A mobile terminal including a first frame; a second frame configured to move from the first frame in a first direction to switch the mobile terminal from a first state to a second state and to slidably move toward the first frame in a second direction to switch the mobile terminal from the second state to the first state; a slide frame configured to move in the first direction or the second direction with respect to the second frame; a flexible display including a first region coupled to the first frame, a second region coupled to the slide frame, and a third region disposed between the first region and the second region, the third region flexibly bending around the second frame; and a drive unit configured to move the second frame in the first direction.

Abstract: A radio frequency module includes: a module substrate that includes a principal surface on which external-connection terminals are disposed; a power amplifier that is disposed on the principal surface of the module substrate and amplifies a radio frequency transmission signal; and a heat dissipator that dissipates heat of the power amplifier. The heat dissipator includes: a heat dissipation plate that covers a surface of the power amplifier which is opposite to a surface that faces the module substrate; and at least a first leg that extends from the heat dissipation portion toward the principal surface of the module substrate.

Abstract: Learning means 701 learns a model for identifying an object indicated by data by using training data. First identification means 702 identifies the object indicated by the data by using the model learned by the learning means 701. Second identification means 703 identifies the object indicated by the data as an identification target used by the first identification means 702 by using a model different from the model learned by the learning means 701. The learning means 701 re-learns the model by using the training data including the label for the data determined based on the identification result derived by the second identification means 703 and the data.

Abstract: A novel distributed method for machine learning is described, where the algorithm operates on a plurality of data silos, such that the privacy of the data in each silo is maintained. In some embodiments, the attributes of the data and the features themselves are kept private within the data silos. The method includes a distributed learning algorithm whereby a plurality of data spaces are co-populated with artificial, evenly distributed data, and then the data spaces are carved into smaller portions whereupon the number of real and artificial data points are compared. Through an iterative process, clusters having less than evenly distributed real data are discarded. A plurality of final quality control measurements are used to merge clusters that are too similar to be meaningful. These distributed quality control measures are then combined from each of the data silos to derive an overall quality control metric.

Abstract: One example discloses a near-field wireless device, including: a controller configured to be coupled to a near-field antenna; wherein the near-field antenna includes, a near-field electric antenna configured to transmit and/or receive near-field electric (E) signals; and a near-field magnetic antenna configured to transmit and/or receive near-field magnetic (H) signals; a conductivity monitor configured to determine a conductivity of a medium proximate to the near-field device; wherein the controller is configured to modulate an E/H ratio of fields generated by and/or received from the near-field electric (E) antenna and the near-field magnetic (H) antenna based on the conductivity of the medium.

Abstract: The proposed invention aims at encoding contextual information for video analysis and understanding, by encoding spatial and temporal relationships of objects and the main agent in a scene. The main target application of the invention is human activity recognition. The encoding of such spatial and temporal relationships may be crucial to distinguish different categories of human activities and may be important to help in the discrimination of different video categories, aiming at video classification, retrieval, categorization and other video analysis applications.

Abstract: Methods, systems, and computer program products for determining operating range of hyperparameters are provided herein. A computer-implemented method includes obtaining a machine learning model, a list of candidate values for a hyperparameter, and a dataset; performing one or more hyperparameter range trials based on the machine learning model, the list of candidate values for the hyperparameter, and the dataset; automatically determining an operating range of the hyperparameter based on the one or more hyperparameter range trials; and training the machine learning model to convergence based at least in part on the determined operating range.