Systems and methods are provided for medical image classification of images from varying sources. A set of microscopic medical images are acquired, and a first neural network module configured to reduce each of the set of microscopic medical images to a feature representation is generated. The first neural network module, a second neural network module, and a third neural network module are trained on at least a subset of the set of microscopic medical images. The second neural network module is trained to receive feature representation associated with an image of the microscopic images and classify the image into one of a first plurality of output classes. The third neural network module is trained to receive the feature representation, classify the image into one of a second plurality of output classes based on the feature representation, and provide feedback to the first neural network module.

A method for image segmentation includes (a) clustering, based upon k-means clustering, pixels of an image into first clusters, (b) outputting a cluster map of the first clusters (c) re-clustering the pixels into a new plurality of non-disjoint pixel-clusters, and (d) classifying the non-disjoint pixel-clusters in categories, according to a user-indicated classification. Another method for image segmentation includes (a) forming a graph with each node of the graph corresponding to a first respective non-disjoint pixel-cluster of the image and connected to each terminal of the graph and to all other nodes corresponding to other respective non-disjoint pixel-clusters that, in the image, are within a neighborhood of the first respective non-disjoint pixel-cluster, (b) setting weights of connections of the graph according to a user-indicated classification in categories respectively associated with the terminals, and (c) segmenting the image into the categories by cutting the graph based upon the weights.

An information processing device configured to: specify, from a moving image obtained by imaging work of a person, a first plurality of stationary positions at which the person is stationary and a movement order in which the person moves through the first plurality of stationary positions, divide the first plurality of stationary positions into a first plurality of clusters by clustering the first plurality of stationary positions, when a cluster included in the first plurality of clusters includes a pair of stationary positions with a relationship of a movement source and a movement destination in the movement order, divide a second plurality of stationary positions included in the cluster into a second plurality of clusters by clustering the second plurality of stationary positions, and generate a region of interest in the moving image based on the second plurality of clusters.

An information processing device configured to: specify, from a moving image obtained by imaging work of a person, a first plurality of stationary positions at which the person is stationary and a movement order in which the person moves through the first plurality of stationary positions, divide the first plurality of stationary positions into a first plurality of clusters by clustering the first plurality of stationary positions, when a cluster included in the first plurality of clusters includes a pair of stationary positions with a relationship of a movement source and a movement destination in the movement order, divide a second plurality of stationary positions included in the cluster into a second plurality of clusters by clustering the second plurality of stationary positions, and generate a region of interest in the moving image based on the second plurality of clusters.

When it is assumed that a large-scale Deep Neural Network for autonomous driving applied compression, there are problems of a decrease in recognition accuracy of a post-compression Neural Network (NN) model and an increase in a compression design period, due to a large number of harmful or unnecessary training images (invalid training images). A training image selection unit B100 calculates an influence value on an inference, and generates an indexed training image set 1004-1 necessary for an NN compression design, by using the influence value. A neural network compression unit P200 notified of the result via a memory P300 compresses the NN.

Disclosed is an artificial intelligence or machine learning algorithm that may be applied to a plurality of machine learning devices in a 5G environment connected to perform the Internet of things. A machine learning method by a first learning machine according to one embodiment of the present disclosure may include obtaining input data; determining, from among a plurality of clusters, a cluster to which the input data belongs, by using a first artificial neural network; transmitting a plurality of sample features associated with the determined cluster to a second learning device using a second artificial neural network; receiving a label for the plurality of sample features from the second learning device, in response to the transmission; and associating the received label with the determined cluster.

One or more images of a portion of a wafer with fabricated devices are acquired using an imaging tool. A pattern of repeating features in an input image of a wafer is identified using various methods, such as correlation and clustering of neighboring vectors. A template is generated based on the found pattern of repeating features. The template is aligned with the acquired image to identify target locations. The target locations are then isolated from the original image for performing detailed metrology.

One or more images of a portion of a wafer with fabricated devices are acquired using an imaging tool. A pattern of repeating features in an input image of a wafer is identified using various methods, such as correlation and clustering of neighboring vectors. A template is generated based on the found pattern of repeating features. The template is aligned with the acquired image to identify target locations. The target locations are then isolated from the original image for performing detailed metrology.

In various examples, potentially highlight-worthy video clips are identified from a gameplay session that a gamer might then selectively share or store for later viewing. The video clips may be identified in an unsupervised manner based on analyzing game data for durations of predicted interest. A classification model may be trained in an unsupervised manner to classify those video clips without requiring manual labeling of game-specific image or audio data. The gamer can select the video clips as highlights (e.g., to share on social media, store in a highlight reel, etc.). The classification model may be updated and improved based on new video clips, such as by creating new video-clip classes.

Embodiments include techniques to determine a set of credit risk assessment data samples, generate local credit risk assessment attributions for the set of credit risk assessment samples, and normalize each local credit risk assessment attribution of the local credit risk assessment attributions. Further, embodiments techniques to compare each pair of normalized local credit risk assessment attributions and assign a rank distance thereto proportional to a degree of ranking differences between the pair of normalized local credit risk assessment attributions. The techniques also include applying a K-medoids clustering algorithm to generate clusters of the local risk assessment attributions, generating global attributions, and determining insights for the neural network based on the global attributions.