A method includes receiving, from sensors, current trace data including current sensor values associated with producing products. The method further includes processing the current trace data to identify features of the current trace data and providing the features of the current trace data as input to a trained machine learning model that uses a hyperplane limit for product classification. The method further includes obtaining, from the trained machine learning model, outputs indicative of predictive data associated with the hyperplane limit and processing the predictive data and the hyperplane limit to determine: first products associated with a first product classification and second products associated with a second product classification based exclusively on the subset of the plurality of features; and third products associated with the first product classification or the second product classification based on an additional feature not within the subset.

A method includes receiving input data associated with an application, the input data including at least one complex object and converting the at least one complex objects of the input data to a linearized set of features. The method further includes performing an explainability service on the application in view of the linearized set of features of the at least one complex object to generate an explanation array.

This application discloses a data processing method, applied to the field of artificial intelligence, including: obtaining to-be-processed data; and processing the to-be-processed data by using a trained neural network, to output a processing result. The neural network includes a feature extraction network and a classification network. The feature extraction network is configured to extract a feature vector expressed by the to-be-processed data in hyperbolic space. The classification network is configured to process the feature vector based on an operation rule of the hyperbolic space, to obtain the processing result. In this application, precision of processing by a model a data set including a tree-like hierarchical structure can be improved, and a quantity of model parameters can be reduced.

This application discloses a data processing method, applied to the field of artificial intelligence, including: obtaining to-be-processed data; and processing the to-be-processed data by using a trained neural network, to output a processing result. The neural network includes a feature extraction network and a classification network. The feature extraction network is configured to extract a feature vector expressed by the to-be-processed data in hyperbolic space. The classification network is configured to process the feature vector based on an operation rule of the hyperbolic space, to obtain the processing result. In this application, precision of processing by a model a data set including a tree-like hierarchical structure can be improved, and a quantity of model parameters can be reduced.

Apparatuses, systems, and techniques are presented to classify objects in images. In at least one embodiment, one or more neural networks are used to identify one or more objects in one or more full images based, at least in part, on the one or more neural networks having been trained using the one or more full images and one or more portions of the one or more full images.

A processor system comprises a memory organizer unit and a matrix computing unit. The memory organizer unit is configured to receive a request for a three-dimensional data of a convolutional neural network layer. The requested three-dimensional data is obtained from a memory. The obtained three-dimensional data is rearranged in an optimized linear order and the rearranged data in the optimized linear order is provided to the matrix computing unit. The matrix computing unit is configured to perform at least a portion of a three-dimensional convolution using at least a portion of the provided rearranged data in the optimized linear order.

A processor system comprises a memory organizer unit and a matrix computing unit. The memory organizer unit is configured to receive a request for a three-dimensional data of a convolutional neural network layer. The requested three-dimensional data is obtained from a memory. The obtained three-dimensional data is rearranged in an optimized linear order and the rearranged data in the optimized linear order is provided to the matrix computing unit. The matrix computing unit is configured to perform at least a portion of a three-dimensional convolution using at least a portion of the provided rearranged data in the optimized linear order.

Mechanisms are provided for determining a measure of radiodensity of anatomical structures of interest and classifying medical imaging study data structures (studies) with regard to contrast phase. In some embodiments, this classification may be used to select/exclude slices for processing by other downstream computing systems. A subset of slices are selected from the study and, for each slice in the subset, a corresponding body part regression (BPR) score is determined. A linear regression on the BPR scores is performed and a representative slice is selected based on results of the linear regression. The representative slice is segmented and a statistical measure of a radiodensity metric for each segment in the representative slice is determined.

In an information processing apparatus that includes sequences of weak classifiers which are logically cascade-connected in each sequence and the sequences respectively correspond to categories of an object and in which the weak classifiers are grouped into at least a first group and a second group in the order of connection, classification processing by weak classifiers belonging to the first group of respective categories is performed by pipeline processing. Based on the processing results of the weak classifiers belonging to the first group of the respective categories, categories in which classification processing by weak classifiers belonging to the second group is to be performed are decided out of the categories. The classification processing by the weak classifiers respectively corresponding to the decided categories and belonging to the second group is performed by pipeline processing.

There are provided systems and methods for performing object classification through semantic mapping. Such an object classification system includes a system processor, a system memory, and an object categorizing unit stored in the system memory. The system processor is configured to execute the object categorizing unit to receive image data corresponding to an object, and to transform the image data into a directed quantity expressed at least in part in terms of semantic parameters. The system processor is further configured to determine a projection of the directed quantity onto an object representation map including multiple object categories, and to associate the object with a category from among the multiple object categories based on the projection.