Various embodiments, methods and systems for implementing a distributed computing system machine-learning training service are provided. Initially a machine learning model is accessed. A plurality of synthetic data assets are accessed, where a synthetic data asset is associated with asset-variation parameters that are programmable for machine-learning. The machine learning model is retrained using the plurality of synthetic data assets. The machine-learning training service is further configured for executing real-time calls to generate an on-the-fly-generated synthetic data asset such that the on-the-fly-generated synthetic data asset is rendered in real-time to preclude pre-rendering and storing the on-the-fly-generated synthetic data asset. The machine-learning training service further supports hybrid-based machine learning training, where the machine learning model is trained based on a combination of the plurality of synthetic data assets, a plurality of non-synthetic data assets, and synthetic data asset metadata associated with the plurality of synthetic data assets.

A system for updating a descriptor trail using artificial intelligence. The system is configured to display on a graphical user interface operating on a processor connected to a memory an element of diagnostic data. The system is configured to receive from a user client device an element of user constitutional data. The system is configured to display on a graphical user interface the element of user constitutional data. The system is configured to prompt an advisor input on a graphical user interface. The system is configured to receive from an advisor client device an advisor input containing an element of advisory data. The system is configured to generate an updated descriptor trail as a function of the advisor input. The system is configured to display the updated descriptor trail on a graphical user interface.

A method for controlling a robotic device is presented. The method includes positioning the robotic device within a task environment. The method also includes mapping descriptors of a task image of a scene in the task environment to a teaching image of a teaching environment. The method further includes defining a relative transform between the task image and the teaching image based on the mapping. Furthermore, the method includes updating parameters of a set of parameterized behaviors based on the relative transform to perform a task corresponding to the teaching image.

The disclosure provides an internal thermal fault diagnosing method for an oil-immersed transformer based on DCNN and image segmentation, including: 1) dividing an internal area of a transformer, and using fault areas and normal status as labels of DCNN; 2) through lattice Boltzmann simulation, randomly obtaining multiple feature images of the internal temperature field distribution of the transformer under normal and various fault state modes, and the fault area serves as a label to form the underlying training sample set; 3) obtaining historical monitoring information of the infrared camera or temperature sensor, and forming its corresponding fault diagnosis results into labels; 4) combining all monitoring information contained in each sample into one image, and then extracting the same monitoring information from the samples in the sample set to form a new image; 5) segmenting image sample and then inputting the same into DCNN for training to obtain diagnosis results.

In collection of training data for image recognition, in order to support a reduction in collection of improper images which are not suitable as training data, a learning data collection device includes a processor which is configured to acquire a captured image from an image capturing device, determine whether or not the captured image is suitable as training data, and when the captured image is determined to be not suitable as training data, perform a notification operation to prompt an image capturing person to reshoot a new image for the captured image.

The invention relates to a computer-implemented method for automatically detecting anatomical structures (3) in a medical image (1) of a subject, the method comprising applying an object detector function (4) to the medical image, wherein the object detector function performs the steps of: (A) applying a first neural network (40) to the medical image, wherein the first neural network is trained to detect a first plurality of classes of larger-sized anatomical structures (3a), thereby generating as output the coordinates of at least one first bounding box (51) and the confidence score of it containing a larger-sized anatomical structure; (B) cropping (42) the medical image to the first bounding box, thereby generating a cropped image (11) containing the image content within the first bounding box (51); and (C) applying a second neural network (44) to the cropped medical image, wherein the second neural network is trained to detect at least one second class of smaller-sized anatomical structures (3b), thereby generating as output the coordinates of at least one second bounding box (54) and the confidence score of it containing a smaller-sized anatomical structure.

The invention relates to a computer-implemented method for automatically detecting anatomical structures (3) in a medical image (1) of a subject, the method comprising applying an object detector function (4) to the medical image, wherein the object detector function performs the steps of: (A) applying a first neural network (40) to the medical image, wherein the first neural network is trained to detect a first plurality of classes of larger-sized anatomical structures (3a), thereby generating as output the coordinates of at least one first bounding box (51) and the confidence score of it containing a larger-sized anatomical structure; (B) cropping (42) the medical image to the first bounding box, thereby generating a cropped image (11) containing the image content within the first bounding box (51); and (C) applying a second neural network (44) to the cropped medical image, wherein the second neural network is trained to detect at least one second class of smaller-sized anatomical structures (3b), thereby generating as output the coordinates of at least one second bounding box (54) and the confidence score of it containing a smaller-sized anatomical structure.

The disclosure relates to a method for training a first neural network, in particular for generating training data for at least one second neural network, using a controller, wherein measurement data ascertained by at least one surroundings sensor or artificially generated data of initially ten traffic scenarios is received, the received measurement data is fed to the first neural network as input data in order to train the first neural network, and the first neural network which is trained on the basis of the input data is used to generate data of traffic scenarios which differ from the initial traffic scenarios. Furthermore, the disclosure relates to a method for training at least one second neural network, to a controller, to a computer program, and to a machine-readable storage medium.

The disclosure relates to a method for training a first neural network, in particular for generating training data for at least one second neural network, using a controller, wherein measurement data ascertained by at least one surroundings sensor or artificially generated data of initially ten traffic scenarios is received, the received measurement data is fed to the first neural network as input data in order to train the first neural network, and the first neural network which is trained on the basis of the input data is used to generate data of traffic scenarios which differ from the initial traffic scenarios. Furthermore, the disclosure relates to a method for training at least one second neural network, to a controller, to a computer program, and to a machine-readable storage medium.

An image recognition method includes: obtaining a to-be-recognized image; determining whether the image is a forged image by recognizing the image through a trained generative adversarial network, the generative adversarial network including a generator and a classifier. Training the classifier includes: obtaining an original image group having a plurality of original images, and a category label of each original image. Each of the plurality of original images includes a real image and a forged image corresponding to the real image. The method includes obtaining using the classifier, for a respective original image of the plurality of original images, first-type noise corresponding to the respective original image; inputting the respective original image into the generator to obtain an output of the generator, and obtaining second-type noise corresponding to the respective original image as the output; and training the classifier using the respective original image, the first-type noise, and the second-type noise.