Abstract: A method for selecting a deep learning network which is optimal for solving an image processing task obtaining a type of the image processing task, selecting a data set according to the type of problem, and dividing selected data set into training data and test data. Similarities between different training data are calculated, and a batch size of the training data is adjusted according to the similarities of the training data. A plurality of deep learning networks is selected according to the type of problem, and the plurality of deep learning networks is trained through the training data to obtain network models. Each of the network models is tested through the test data, and the optimal deep learning network with the best test result is selected from the plurality of deep learning networks appropriate for image processing.

Abstract: A learning method implemented by a computer, includes: creating an input data tensor including a local dimension and a universal dimension by partitioning series data into local units, the series data including a plurality of elements, each of the plurality of elements in the series data being logically arranged in a predetermined order; and performing machine learning by using tensor transformation in which a transformation data tensor obtained by transforming the input data tensor with a transformation matrix is outputted using a neural network, wherein the learning includes rearranging the transformation matrix so as to maximize a similarity to a matching pattern serving as a reference in the tensor transformation regarding the universal dimension of the input data tensor, and updating the matching pattern in a process of the machine learning regarding the local dimension of the input data tensor.

Abstract: An analytics system uses one or more machine-learned models to predict a hormone receptor status from a H&E stain image. The system partitions H&E stain images each into a plurality of image tiles. Bags of tiles are created through sampling of the image tiles. The analytics system trains one or more machine-learned models with training H&E stain images having a positive or negative receptor status. The analytics system generates, via a tile featurization model, a tile feature vector for each image tile a test bag for a test H&E stain image. The analytics system generates, via an attention model, an aggregate feature vector for the test bag by aggregating the tile feature vectors of the test bag, wherein an attention weight is determined for each tile feature vector. The analytics system predicts a hormone receptor status by applying a prediction model to the aggregate feature vector for the test bag.

Abstract: Devices for using a neural network to choose an optimal error correction algorithm are disclosed. An example device includes a decoding controller inputting at least one of the number of primary unsatisfied check nodes (UCNs), the number of UCNs respectively corresponding to at least one iteration, and the number of correction bits respectively corresponding to the at least one iteration to a trained artificial neural network, and selecting any one of a first error correction decoding algorithm and a second error correction decoding algorithm based on an output of the trained artificial neural network corresponding to the input, and an error correction decoder performing error correction decoding on a read vector using the selected error correction decoding algorithm. The output of the trained artificial neural network may include a first predicted value indicating a possibility that a first error correction decoding using the first error correction decoding algorithm is successful.

Abstract: A mold temperature control system includes: an inference model generating portion configured to, based on a plurality of pieces of thermo image data of a mold acquired at predetermined intervals and pieces of teaching data associated with the plurality of pieces of thermo image data, learn a predetermined number of consecutive pieces of time-series image data extracted from the plurality of pieces of thermo image data as one piece of sample data to generate an inference model for detecting a sign of a temperature anomaly of the mold; a mold temperature anomaly degree inference portion configured to detect occurrence of the sign of the temperature anomaly of the mold the predetermined number ahead, using the inference model, based on the predetermined number of pieces of time-series image data of the mold; and a warning lamp request transmitting portion configured to control lighting-up of a warning lamp.

Abstract: Business to Consumer (B2C) systems face a challenge of engaging users since offers are created using static rules generated using clustering on large transactional data generated over a period of time. Moreover, the offer creation and assignment engine is disjoint to the transactional system which led to significant gap between history used to create offers and current activity of users. Systems and methods of the present disclosure provide a meta-model based configurable auto-tunable recommendation model generated by ensembling optimized machine learning and deep learning models to predict a user's likelihood to take an offer and deployed in real time. Furthermore, the offer given to the user is based on a current context derived from the user's recent behavior that makes the offer relevant and increases probability of conversion of the offer to a sale. The system achieves low recommendation latency and scalable high throughput by virtue of the architecture used.

Abstract: Analog gain correction circuitry and analog switching clock edge timing correction circuitry can provide coarse correction of interleaving errors in radio-frequency digital-to-analog converters (RF DACs), such as may be used in 5G wireless base stations. The analog correction can be supplemented by digital circuitry configured to “pre-cancel” an interleaving image by adding to a digital DAC input signal a signal equal and opposite to an interleaving image created by the interleaving DAC, such that the interleaving image is effectively mitigated. Error correction control parameters can be periodically adjusted for changes in temperature by a controller coupled to an on-chip temperature sensor. A model useful for understanding the sources of error in interleaving DACs is also described.

Abstract: Systems and methods for automated custom training of a scoring model are disclosed herein. The method include: receiving a plurality of responses received from a plurality of students in response to providing of a prompt; identifying an evaluation model relevant to the provided prompt, which evaluation model can be a machine learning model trained to output a score relevant to at least portions of a response; generating a training indicator that provides a graphical depiction of the degree to which the identified evaluation model is trained; determining a training status of the model; receiving at least one evaluation input when the model is identified as insufficiently trained; updating training of the evaluation model based on the at least one received evaluation input; and controlling the training indicator to reflect the degree to which the evaluation model is trained subsequent to the updating of the training of the evaluation model.

Abstract: A system and method for training a system or a model using any combination of synthetic data and real data. The various aspects of the invention include generation of data that is used to supplement or augment real data, wherein the subject of the data can be segmented. Labels or attributes are automatically added to generated data. The generated data is synthetic data that is generated using seed or real data as well as from other synthetic data. Using the synthetic data, various domain adaptation models can be used and trained.

Abstract: A system and method for training a model using a training dataset. The training dataset can be made up of only real data, only synthetic data, or any combination of synthetic data and real data. The images are segmented to define objects with known labels. The object is pasted onto backgrounds to generated synthetic datasets. The various aspects of the invention include generation of data that is used to supplement or augment real data. Labels or attributes can be automatically added to the data as it is generated. The data can be generated using seed data. The data can be generated using synthetic data. The data can be generated from any source, including the user's thoughts or memory. Using the training dataset, various domain adaptation models can be trained.

Abstract: A device receives a machine learning model, model data associated with the machine learning model, and identifier generation data. The identifier generation data includes data utilized to generate identifier pairs that may be used to authenticate the machine learning model. The device selects an identifier model, for generating the identifier pairs, based on the machine learning model, the model data, and the identifier generation data. The device processes the machine learning model, the model data, and the identifier generation data, with the selected identifier model, to generate the identifier pairs and identifier pair data. The device stores the identifier pairs and the identifier pair data in one or more data structures, and utilizes the identifier pairs to identify and provide authentication for the machine learning model.

Abstract: An electrocardiogram (ECG) interpretation system is operable to receive a captured image of an ECG printout. A waveform detection function is performed on the captured image to determine a plurality of locations of a plurality of ECG waveforms in the captured image. A plurality of waveform images are generated by partitioning the captured image based on the plurality of locations, where each of the plurality of waveform images includes one of the plurality of ECG waveforms. A plurality of pseudo-raw ECG signal data is generated by performing a signal reconstruction function on each of the plurality of waveform images, where each of the plurality of pseudo-raw ECG signal data corresponds to one of the plurality of waveform images. Diagnosis data is generated by performing a diagnosing function on the plurality of pseudo-raw ECG signal data. The diagnosis data is transmitted to a client device for display via a display device.

Abstract: A system for verifying authenticity of an anti-counterfeiting element includes a model building module and a verifying module. The model building module has a pre-processing sub-module for receiving original images of a same reference element and for making adjustments to the original images to form a plurality of true-element images. A training sub-module trains a deep neural network based on the true-element images to build a machine learning model. The verifying module obtains images of the anti-counterfeiting element, and inputs the images into the machine learning model to determine whether the anti-counterfeiting element is authentic or unauthentic.

Abstract: Computer technology for sending an image a device to be authenticated. The image is designed to be classified to a first category by an image classifier, and the first category is different from a nature category of the image. A response message can be received from the device. The response message indicates a second category of the image determined by the device. Then, the device is determined to be an authorized device in response to the second category being consistent with the first category.

Abstract: A system and method are disclosed for training a model using a training dataset. The training dataset can include only real data, only synthetic data, or any combination of synthetic data and real data. The various aspects of the invention include generation of data that is used to supplement or augment real data. Labels or attributes can be automatically added to the data as it is generated. The data can be generated using seed data. The data can be generated using synthetic data. The data can be generated from any source, including the user's thoughts or memory. Using the training dataset, various domain adaptation models can be trained.

Abstract: A system and method are disclosed for training a system or a model using any combination of synthetic data and real data. The various aspects of the invention include generation of data that is used to supplement or augment real data, wherein the subject of the data can be segmented. Labels or attributes are automatically added to generated data. The generated data is synthetic data that is created using the seed or real data as well as from other synthetic data. Using the synthetic data, various domain adaptation models can be used and trained for unsupervised domain adaptation.

Abstract: A neural network is trained to focus on a domain of interest. For example, in a pre-training phase, the neural network in trained using synthetic training data, which is configured to omit or limit content less relevant to the domain of interest, by updating parameters of the neural network to improve the accuracy of predictions. In a subsequent training phase, the pre-trained neural network is trained using real-world training data by updating only a first subset of the parameters associated with feature extraction, while a second subset of the parameters more associated with policies remains fixed.

Abstract: A device that generates a location estimation model is provided. The location estimation model generator device includes a map generator part configured to generate a magnetic field map, which includes magnetic field values corresponding respectively to the coordinates of an indoor space; a data generator part configured to generate learning data by implementing the magnetic field map; and a learning part configured to generate a location estimation model by artificial neural network (ANN) learning implementing the learning data.

Abstract: An image processing system accesses an image of a completed form document. The image of the form document includes one or more features, such as form text, at particular locations within the image. The image processing system accesses a template of the form document and computes a rotation and zoom of the image of the form document relative to the template of the form document based on the locations of the features within the image of the form document relative to the locations of the corresponding features within the template of the form document. The image processing system performs a rotation operation and a zoom operation on the image of the form document, and extracts data entered into fields of the modified image of the form document. The extracted data can be then accessed or stored for subsequent use.

Abstract: Symbols are received on a downstream channel. A value of a channel synchronization parameter is determined based on the received symbols. An interference event on the downstream channel is detected. In response to detecting the interference event: an output signal is determined based on at least one cached value of the channel synchronization parameter, the at least one cached value being determined based on symbols received prior to and offset from the detecting of the interference event.