A system includes a cloud computing system having a server, and a user environment computing system having an edge electronic device and a group of edge side sensors installed on at least one of inside and outside of the edge electronic device, the cloud computing system and the user environment computing system connected via a network line. The user environment computing system transfers a plurality of kinds of detection data collected by the group of edge side sensors to the cloud computing system for learning of an inference model generated by the server. When detection data is newly obtained from one sensor out of the group of edge side sensors and the detection data newly obtained is related to the inference model, the detection data newly obtained is transferred to the server for additional learning of the inference model.

The present disclosure discloses an image processing method and related device thereof. The method includes: acquiring an image to be processed; and performing a feature extraction process on the image to be processed using a target neural network so as to obtain target feature data of the image to be processed, wherein parameters of the target neural network are time average values of parameters of a first neural network which is obtained from training under supervision by a training image set and an average network, and parameters of the average network are time average values of parameters of a second neural network which is obtained from training under supervision by the training image set and the target neural network. A corresponding device is also disclosed. Feature data of image to be processed are obtained via the feature extraction process performed on the image to be processed.

A computer-implemented method, a computing system, and a computer program product, for automatically labeling an amount of unlabeled data for training one or more classifiers of a machine learning system. A method includes iteratively processing unlabeled data items. Receiving an unlabeled data item into each autoencoder in an autoencoder architecture. Each autoencoder processing with a lowest loss of information the unlabeled data item that is likely associated with a label associated with the autoencoder, while processing with a higher loss of information the unlabeled data item that is likely not associated with the label. Predicting, based on loss of information, a probability distribution for the unlabeled data item. Automatically associating the label to the unlabeled data item, based on the label being associated with a highest probability in a peaking probability distribution associated with the unlabeled data item. The autoencoder architecture can include a cloud computing network architecture.

A method, a computing device, and a non-transitory machine-readable medium for classifying documents. A document collection is sorted into a plurality of categories. A classifier corresponding to a category of the plurality of categories is trained to output a probability that a document associated with the category is of a selected type (e.g., confidential). The training includes determining, by the processor, that a cardinality of a set of negative samples in a train set is not above a pipeline threshold but is at least one and training the classifier via a first pipeline and a second pipeline using a training group that includes a first portion of a group of positive samples in the train set, a second portion of a set of negative samples in the train set, and a third portion of a group of unlabeled samples in the train set

A sequence of images depicting an object is captured, e.g., by a camera at a point-of-sale terminal in a retail store. The object is identified, such as by a barcode or watermark that is detected from one or more of the images. Once the object's identity is known, such information is used in training a classifier (e.g., a machine learning system) to recognize the object from others of the captured images, including images that may be degraded by blur, inferior lighting, etc. In another arrangement, such degraded images are processed to identify feature points useful in fingerprint-based identification of the object. Feature points extracted from such degraded imagery aid in fingerprint-based recognition of objects under real life circumstances, as contrasted with feature points extracted from pristine imagery (e.g., digital files containing label artwork for such objects). A great variety of other features and arrangements—some involving designing classifiers so as to combat classifier copying—are also detailed.

A computer-implemented method and systems are provided for performing machine learning for an image classification task. The method includes overlaying, by a processor, a second image on a first image to form a mixed image, by averaging an intensity of each of a plurality of co-located pixel pairs in the first and the second image. The method also includes training, by the processor, a machine learning process configured for the image classification task using the mixed image to augment data used by the machine learning process for the image classification task.

A method and system for generating music uses artificial intelligence to analyze existing musical compositions and then creates a musical composition that deviates from the learned styles. Known musical compositions created by humans are presented in digitized form along with a style designator to a computer for analysis, including recognition of musical elements and association of particular styles. A music generator generates a draft musical composition for similar analysis by the computer. The computer ranks such draft musical composition for correlation with known musical elements and known styles. The music generator modifies the draft musical composition using an iterative process until the resulting musical composition is recognizable as music but is distinctive in style.

An image processing method includes acquiring consecutive time-series images captured by an onboard camera and including at least one image having a first annotation indicating a first region; determining, for each of the images, in reverse chronological order from an image of the last time point, whether the first region exists in the image based on whether the first annotation is attached; identifying the first image of a first time point for which the first region is determined not to exist, and setting a second region including a partial region of an object in the identified first image, indicating the moving object that is obstructed by the object before appearing on the path, and having dimensions based on dimensions of the first region in an image of a second time point immediately after the first time point; and attaching a second annotation to the image corresponding to the second time point, the second annotation indicating the second region.

A method of ball trajectory tracking, the method comprising computer executable steps of: receiving a plurality of training frames, each one of the training frames showing a trajectory of a ball as a series of one or more elements, using the received training frames, training a first neuronal network to locate a trajectory of a ball in a frame, receiving a second frame, and using the first neuronal network, locating a trajectory of a ball in the second frame, the trajectory being shown in the second frame as a series of images of the ball having the located trajectory.

A computer-implemented method for training a machine learning system including: initializing parameters of the machine learning system and a metaparameter. Repeatedly carrying out the following as a loop: providing a batch of training data points and manipulating the provided training data points or a training method for optimizing the parameters of the machine learning system or a structure of the machine learning system based on the metaparameter. Ascertaining a cost function as a function of instantaneous parameters of the machine learning system and of the instantaneous metaparameters. Adapting the instantaneous parameters as a function of an ascertained first gradient, which has been ascertained with respect to the instantaneous parameters via the ascertained cost function for the training data points, and adapting the metaparameter as a function of a second gradient, which has been ascertained with respect to the metaparameter used in the preceding step via the ascertained cost function.