Abstract: A protein searcher includes a pre-trained CNN, a feature extractor, a database and a KNN searcher. The pre-trained CNN, trained on a previously classified amino acid database, receives an unidentified amino acid sequence. The feature extractor extracts a feature vector of the unidentified amino acid sequence as a query feature vector. The database stores feature vectors of trained amino acid sequences and of at least one untrained amino acid sequence and stores associated classes of the trained amino acid sequences and associated tags of the at least one untrained amino acid sequence. The KNN searcher finds K feature vectors of the database which are close to the query feature vector and outputs the associated class or tag of each of the K feature vectors.

Abstract: An embodiment of a mobile communication system includes a plurality of mobile units operating within a defined operating area, each of the mobile units having a processor, a memory for storing a mobile unit file structure, an application running on the processor for operating on the mobile unit file structure, and a receiver for receiving on a common receive communication channel data. The mobile communication system further includes a plurality of geolocation markers disposed within the defined operating area, each having a memory for storing geolocation information to define a relative position within the defined operating area, and a geolocation transmitter for transmitting the defined geolocation information on the common receive communication channel, the geolocation transmitter having a geolocation transmit range less than the defined operating area.

Abstract: A perception system is adapted to receive visual data from a camera and includes a controller having a processor and tangible, non-transitory memory on which instructions are recorded. A subsampling module, an object detection module and an attention module are each selectively executable by the controller. The controller is configured to sample an input image from the visual data to generate a rescaled whole image frame, via the subsampling module. The controller is configured to extract feature data from the rescaled whole image frame, via the object detection module. A region of interest in the rescaled whole image frame is identified, based on an output of the attention module. The controller is configured to generate a first image based on the rescaled whole image frame and a second image based on the region of interest, the second image having a higher resolution than the first image.

Abstract: Apparatuses, systems, and techniques to identify out-of-distribution input data in one or more neural networks. In at least one embodiment, a technique includes training one or more neural networks to infer a plurality of characteristics about input information based, at least in part, on the one or more neural networks being independently trained to infer each of the plurality of characteristics about the input information.

Abstract: A method for generating a digital 3D representation of at least a part of an intraoral cavity, the method including recording a plurality of views containing surface data representing at least the geometry of surface points of the part of the intraoral cavity using an intraoral scanner; determining a weight for each surface point at least partly based on scores that are measures of belief of that surface point representing a particular type of surface; executing a stitching algorithm that performs weighted stitching of the surface points in said plurality of views to generate the digital 3D representation based on the determined weights; wherein the scores for the surface points are found by at least one score-finding algorithm that takes as input at least the geometry part of the surface data for that surface point and surface data for points in a neighbourhood of that surface point.

Abstract: Multi-radio antenna apparatuses and stations for wireless networks including multiple radios coupled to a single transmit/receive antenna, in which the antenna is highly synchronized by an external (e.g., GPS) signal. These multi-radio antenna systems may provide highly resilient links. Synchronization may allow these apparatuses to organically scale the transmission throughput while preventing data loss. The single transmit/receive antenna may have a single dish or a compound (e.g., a single pair of separate transmitting and receiving dishes) and connections for two or more radios.

Abstract: Systems and methods for training and utilizing predictive models that ignore missing features in accordance with embodiments of the invention are illustrated. One embodiment includes a method for generating representations of inputs with missing values. The method includes steps for, at a single layer in a multi-layer model, receiving an input includes a set of one or more values for several features and identifying a missingness pattern of the input, wherein the missingness pattern indicates whether the set of values is missing a value for each of the several features. The method further includes determining a set of one or more transformation weights based on the missingness pattern and transforming the input based on the determined transformation weights.

Abstract: One or more embodiments of the present disclosure include systems and methods that use neural architecture fusion to learn how to combine multiple separate pre-trained networks by fusing their architectures into a single network for better computational efficiency and higher accuracy. For example, a computer implemented method of the disclosure includes obtaining multiple trained networks. Each of the trained networks may be associated with a respective task and has a respective architecture. The method further includes generating a directed acyclic graph that represents at least a partial union of the architectures of the trained networks. The method additionally includes defining a joint objective for the directed acyclic graph that combines a performance term and a distillation term. The method also includes optimizing the joint objective over the directed acyclic graph.

Abstract: Methods, systems, and computer readable media for model-based robust deep learning. In some examples, a method includes obtaining a model of natural variation for a machine learning task. The model of natural variation includes a mapping that specifies how an input datum can be naturally varied by a nuisance parameter. The method includes training, using the model of natural variation and training data for the machine learning task, a neural network to complete the machine learning task such that the neural network is robust to natural variation specified by the model of natural variation.

Abstract: Systems and methods for using image analysis techniques to assess unsafe driving conditions by a vehicle operator are discloses. According to aspects, a computing device may access and analyze image data depicting the vehicle operator. In analyzing the image, the computing device may measure certain visible metrics as depicted in the image data and compare the metrics to corresponding threshold values, and may accordingly determine whether the vehicle operator is exhibiting an unsafe driving condition. The computing device may generate and present alerts that indicate any determined unsafe driving condition.

Abstract: An operating method of a computing apparatus is provided. The operating method of the computing apparatus includes obtaining a reference image; obtaining a distorted image generated from a reference image; obtaining an objective quality assessment score of a distorted image that is indicative of a quality of a distorted image as assessed by an algorithm, by using a reference image and a distorted image; obtaining a subjective quality assessment score corresponding to a objective quality assessment score; and training a neural network, by using a distorted image and a subjective quality assessment score as a training data set.

Abstract: Neural network-based categorization can be improved by incorporating graph neural networks that operate on a graph representing the taxonomy of the categories into which a given input is to be categorized by the neural network based-categorization. The output of a graph neural network, operating on a graph representing the taxonomy of categories, can be combined with the output of a neural network operating upon the input to be categorized, such as through an interaction of multidimensional output data, such as a dot product of output vectors. In such a manner, information conveying the explicit relationships between categories, as defined by the taxonomy, can be incorporated into the categorization. To recapture information, incorporate new information, or reemphasize information a second neural network can also operate upon the input to be categorized, with the output of such a second neural network being merged with the output of the interaction.

Abstract: The present disclosure provides a medical image segmentation method. The medical image segmentation method includes acquiring a to-be-processed medical image set, the to-be-processed medical image set including a plurality of to-be-processed medical images corresponding to different time points, processing the to-be-processed medical image set in a time dimension according to the to-be-processed medical images and the time points corresponding to the to-be-processed medical images to obtain a temporal dynamic image, and extracting a target region feature from the temporal dynamic image by using a medical image segmentation model, to acquire a target region.

Abstract: A food-recognition engine can be used with a mobile device to identify, in real-time, foods present in a video stream. To capture the video stream, a user points a camera of the mobile device at foods they are about to consume. The video stream is displayed, in real-time, on a screen of the mobile device. The food-recognition engine uses several neural networks to recognize, in the video stream, food features, text printed on packaging, bar codes, logos, and “Nutrition Facts” panels. The neural-network outputs are combined to identify foods with high probabilities. The foods may be packaged or unpackaged, branded or unbranded, and labeled or unlabeled, and may appear simultaneously within the view of the mobile device. Information about recognized foods is displayed on the screen while the video stream is captured. The user may log identified foods with a gesture and without typing.

Abstract: Multimodal techniques are described for classifying start pages and document types of an unstructured document image package. To that end, some implementations of the disclosure relate to a method, including: obtaining a document image file including multiple pages and multiple document types; generating, for each page of the multiple pages, using multiple independent trained models, multiple independent predictions, each of the multiple independent predictions indicating: whether or not the page is a first page of a document, or a document type of the multiple document types that the page corresponds to; and generating, for each page of the multiple pages, based on the multiple independent predictions, using a neural network, a final prediction output indicating whether or not the page is the first page of a document, or one of the multiple document types that the page corresponds to.

Abstract: Briefly, in accordance with one or more embodiments, a user equipment (UE) may enter into an E-UTRAN Routing Area Paging Channel state, and is configured with an E-UTRAN Routing Area and an Anchor identifier to identify an anchor evolved Node B (eNB) for the UE. The UE selects to a new cell without performing a handover procedure, and performs a cell update procedure. The UE also may enter into a Cell Update Connected state, and is configured with an Anchor identifier. The UE selects to a new cell, performs a cell update procedure, performs a buffer request procedure, and performs a cell update procedure to download buffered data and to perform data transmission with the new cell.

Abstract: Aspects of the present invention provide methods, apparatuses, systems, computing devices, computing entities, and/or the like for identifying data processing activities associated with various data assets based on data discovery results. In accordance various aspects, a method is provided comprising: identifying and scanning data assets to detect a subset of the data assets, wherein each asset of the subset is associated with a particular data element used for target data; generating a prediction for each pair of data assets of the subset on the target data flowing between the pair; identifying a data flow for the target data based on the prediction generated for each pair; and identifying a data processing activity associated with handling the target data based on a correlation identified for the particular data element, the subset, and/or the data flow with a known data element, subset, and/or data flow for the data processing activity.

Abstract: A system comprises a combination of digital fingerprint authentication techniques, processes, programs, and hardware to facilitate highly reliable authentication of a wide variety of composite physical objects. “Composite” in this case means that there are distinct regions of the object that must be authenticating individually and in tandem to authenticate the entire object. Preferably, a template is stored that defines for a class of objects what regions must be found, their locations, optionally semantic content of the regions, and other criteria. digital fingerprinting is utilized to locate and attempt to match candidate regions by querying a database of reference object records.

Abstract: Techniques are generally described for fusing sensor data of different modalities using a transformer. In various examples, first sensor data may be received from a first sensor and second sensor data may be received from a second sensor. A first feature representation of the first sensor data may be generated using a first machine learning model and a second feature representation of the second sensor data may be generated using a second machine learning model. In some examples, a modified first feature representation of the first sensor data may be generated based at least in part on a self-attention mechanism of a transformer encoder. The modified first feature representation may be generated based at least in part on the first feature representation and the second feature representation. A computer vision task may be performed using the modified first feature representation.

Abstract: An urban data prediction method based on a generative causal interpretation model is provided. The generative causal interpretation model includes exogenous variables, spatio-temporal conditional parent variables, controlled causal transition functions, and spatio-temporal mixing functions. By inferring the model's exogenous variables, causal descriptors, spatio-temporal conditional parent variables, and other causal latent variables from the observation data and fitting the corresponding functions such as the controlled causal transfer function and the spatio-temporal mixing function, the invention can predict the spatio-temporal data in city level based on the model. The observation data of the urban complex system can be decomposed into causal descriptors with physical meanings. Under the influence of stable causal structure, the robustness and applicability of the model can be improved, so that the prediction results are more in line with the operation of urban complex systems.