Abstract: A multiplexer includes acoustic wave filters that are electrically connected to a common connection terminal. In a first transmission-side filter of the acoustic wave filters, a series arm resonator closest to the common connection terminal includes acoustic wave resonators that are electrically connected in series and capacitance elements that are electrically connected between at least one of signal paths electrically connecting the acoustic wave resonators to each other and a reference terminal.

Abstract: Techniques for training machine learning models for improved accuracy at classifying medical imaging data sets by trimming ambiguous samples from training data sets are described herein. In some embodiments, a machine learning model is trained using a data set, where a subset of the data set comprises data with a conflict between a first label based on an expert opinion and a second label based on a ground truth based on a medical examination. During some epochs of training the machine learning model, loss values for each data sample in the epoch are compared against a loss threshold, with data samples with corresponding loss values that exceed the loss threshold that also belong to the subclass trimmed from the data set for subsequent epochs of training. The loss threshold for the next epoch is then updated based on loss values of the trimmed data set.

Abstract: A communication apparatus searches for a device using a first wireless communication, instructs, using the first wireless communication, a device selected from a list based the result of the search to operate in an access point mode, obtains, using the first wireless communication, connection information from the device operating in the access point mode, establishes a second wireless connection with the device based on the obtained connection information.

Abstract: The present invention discloses a generative adversarial network-based optimization (GAN-O) method. The method includes: transforming an application into a function optimization problem; establishing a GAN-based function optimization model based on a test function and a test dimension of the function optimization problem, including constructing a generator G and a discriminator D based on the GAN; training the function optimization model by training the discriminator and the generator alternatively, to obtain a trained function optimization model; and using the trained function optimization model to perform iterative calculation to obtain an optimal solution. In this way, the optimal solution is obtained based on the GAN. The present invention can improve the parameter training process of a deep neural network to obtain a better local optimal solution in a shorter time, making the training of the deep neural network more stable and obtaining better local search results.

Abstract: A method includes, at a computer system with a display, a housing, and an attachment mechanism, detecting attachment of an accessory to the computer system, where the accessory, while attached, has a predetermined orientation relative to the attachment mechanism, and in response to detecting the attachment of the accessory to the computer system in accordance with a determination that the accessory is a first accessory with first physical dimensions, displaying, on the display, a first visual indication that the accessory has been attached to the computer system, wherein the first visual indication indicates at least one property of the first physical dimensions, and in accordance with a determination that the accessory is a second accessory with second physical dimensions that are different from the first physical dimensions, displaying, on the display a second visual indication that the accessory has been attached to the computer system, wherein the second visual indication indicates at least one property o

Abstract: A method of automatic labeling of images for supervised machine learning includes obtaining images of roadside objects with a camera mounted to a vehicle, recording a position and orientation of the vehicle within a defined coordinate system while obtaining the images recording position information for each roadside object with the same defined coordinates system as used while recording the position and orientation of the vehicle, and correlating a position of each of the obtained images of the roadside objects with the position information of each roadside object in view of the recorded position and orientation of the vehicle. The images are labeled to identify the roadside objects in view of the correlated position of each of the obtained images of the roadside objects.

Abstract: Techniques described herein relate to semi-supervised training and application of stacked autoencoders and other classifiers for predictive and other purposes. In various embodiments, a semi-supervised model (108) may be trained for sentence classification, and may combine what is referred to herein as a “residual stacked de-noising autoencoder” (“RSDA”) (220), which may be unsupervised, with a supervised classifier (218) such as a classification neural network (e.g., a multilayer perceptron, or “MLP”). In various embodiments, the RSDA may be a stacked denoising autoencoder that may or may not include one or more residual connections. If present, the residual connections may help the RSDA “remember” forgotten information across multiple layers. In various embodiments, the semi-supervised model may be trained with unlabeled data (for the RSDA) and labeled data (for the classifier) simultaneously.

Abstract: An electronic device according to various embodiments of the present invention comprises: a communication circuit; at least one processor electrically connected to the communication circuit; and a memory electrically connected to the processor, wherein the memory can store instructions causing, when executed, the processor to: receive, through the communication circuit, first information indicating the state of the first electronic device from a first electronic device after initiating booting of the first electronic device and before completion of the booting; and control an output device functionally connected to the processor such that state information of the first electronic device is outputted on the basis of the first information. Additionally, other embodiments are possible.

Abstract: A management method according to an embodiment is a management method performed by a management server for managing a plurality of communication devices, and includes receiving information indicating at least one of a position or acceleration detected by each of the plurality of communication devices, and managing a position information list including installation position information for each communication device based on the information received. The managing includes, in a case that a collection mode for collecting at least one of the plurality of communication devices is configured, in response to determining that a target communication device for the collection mode has moved, updating the position information list to delete the installation position information corresponding to the target communication device, and in response to determining that the target communication device has been stationary after moving, keeping the position information list without updating the position information list.

Abstract: Embodiments of the present disclosure provide systems, methods, and computer-readable media that use machine learning models to enable computing devices to detect and identify cosmetic products in face images. In some embodiments, a model training system may gather training data for building the machine learning models by analyzing face images associated with tagging data. In some embodiments, a recommendation system may be configured to use the machine learning models generated by the model training system to detect products in face images, and to add information based on the detected products to a look data store, and/or to provide recommendations for similar looks from the look data store based on the detected products.

Abstract: A transmit filter circuit includes an input terminal, an output terminal, plural series arm resonators, and a parallel arm resonator. The input terminal receives a transmit signal. The output terminal is electrically connected to an antenna. The plural series arm resonators are electrically connected in series with each other on a line between the input and output terminals. The plural series arm resonators include first and second series arm resonators. The first series arm resonator is closest to the output terminal. The second series arm resonator is second closest to the output terminal. A first end of the parallel arm resonator is electrically connected to a node between the first and second series arm resonators. A reference potential is provided to a second end of the parallel arm resonator. The resonant frequency of the first series arm resonator is higher than that of the second series arm resonator.

Abstract: An identification device has a processor configured to carry out plural identification processing by which an individual is identified based on plural acquired data different from each other indicating the individual and, when the identification of the individual by one or more identification processing of the plural identification processing fails and the identification of the individual by one or more other identification processing of the plural identification processing succeeds, learn the at least one identification processing by which the identification of the individual fails.

Abstract: Techniques are provided for evaluating and defining the scope of data-driven deep learning models. In one embodiment, a machine-readable storage medium is provided comprising executable instructions that, when executed by a processor, facilitate performance of operations comprising employing a machine learning model to extract first training data features included in a training data set and first target data features included in a target data set. The operations further comprise determining whether the target data set is within a defined data scope of the training data set based on analysis of correspondences between the first training data features and the first target data feature, and determining whether application of the target data set to a target neural network model developed using the training data set will generate results with an acceptable level of accuracy based on whether the target data set is within the defined data scope.

Abstract: Digital handwriting synthesis techniques and systems are described that are configured to process text represented using text fields into one or more digital ink strokes to represent the text as handwritten data when rendered in a user interface of a computing device. Additionally, the digital handwriting synthesis techniques are configurable using normalization parameters to adjust an output from a machine learning model such that these techniques are extensible across a wide range of machine learning models and may be used to support a wide range of different digital ink styles. Further, the techniques described herein also support customization via “few shot conditioning” in which the digital ink styles may be further customized based on a user input and in this way support previously unseen digital ink styles.

Abstract: Disclosed are methods, systems, and computer-readable medium to perform operations including: capturing, using an image sensor directed at a drilling system, an image feed of movement of a component of the drilling system with respect to a vertical reference line; converting the image feed into a digital representation of the movement of the component, the digital representation including a number of offset pixels from the component to the vertical reference line in the image feed; converting the digital representation into a machine learning (ML), the ML representation including a plurality of vectors each including the number of offset pixels from the component to the vertical reference line at a respective time; training a ML model using the ML representation to characterize the movement of the component as normal or abnormal; and using the trained ML model to characterize the movement of the component in real-time as normal or abnormal.

Abstract: In an embodiment, a method for inspecting and transforming a machine learning model includes receiving a request that includes the machine learning model and a configuration object that provides an indication of a selected strategy. In the embodiment, the method includes creating a partially specified task graph that includes a first placeholder node for a future expanded task node. In the embodiment, the method includes performing a dynamic expansion and execution phase that includes, repeatedly (a) using a cognitive engine to evaluate whether to revise the partially specified task graph based at least in part on the selected strategy, and (b) using a processor-based execution engine to perform an action specified by the complete node. In an embodiment, the dynamic expansion and execution phase repeats until after the cognitive engine adds a consolidated results node.

Abstract: System for image correction in PET is provided. The system may acquire a PET image and a CT image of a subject. The system may generate, based on the PET image and the CT image, an attenuation-corrected PET image of the subject by application of an attenuation correction model. The attenuation correction model may be a trained cascaded neural network including a trained first model and at least one trained second model downstream to the trained first model. During the application of the attenuation correction model, an input of each of the at least one trained second model may include the PET image, the CT image, and an output image of a previous trained model that is upstream and connected to the trained second model.

Abstract: A semiconductor package includes a semiconductor chip formed with a non-volatile semiconductor memory, a resin encapsulation that encapsulates the semiconductor chip, electrodes in a lattice (solder balls) formed and arrayed in a lattice on a bottom surface of the resin encapsulation. The solder balls include a signal electrode formed within the central region of the array and a dummy electrode formed outside the signal electrode.

Abstract: A structure for radiofrequency applications includes: a support substrate of high-resistivity silicon comprising a lower part and an upper part having undergone a p-type doping to a depth D; a mesoporous trapping layer of silicon formed in the doped upper part of the support substrate. The depth D is less than 1 micron and the trapping layer has a porosity rate of between 20% and 60%.

Abstract: Field effect transistors including a source region and a drain region on a substrate, a fin base protruding from a top surface of the substrate, a plurality of fin portions extending upward from the fin base and connecting the source region with the drain region, a gate electrode on the fin portions, and a gate dielectric between the fin portions and the gate electrode may be provided. A top surface of the substrate may include a plurality of grooves (e.g., a plurality of convex portions and a plurality of concave portions). Further, a device isolation layer may be provided to expose upper portions of the plurality of fin portions and to cover top surfaces of the plurality of grooves.