A method, system, and computer programming product for checking that clusters representative of transactional activity of a group of persons exhibits sufficient variability including: receiving transactional data; forming clusters from the received transactional data representing groups of persons that behave similarly; determining that a cluster representing a group of persons that behave similarly is not sufficiently variable; and increasing, in response to the cluster representing the group of persons behaving similarly not being sufficiently variable, the variability of the cluster. Further including, in an embodiment, creating a superset cluster consisting of both the cluster and the parent of the cluster; creating test data using the superset as a baseline; injecting the test data into the superset cluster; determining if the superset cluster rejects the injected test data as an indication of insufficient variability.

A discrete attribute value dataset is obtained that is associated with a plurality of probe spots each assigned a different probe spot barcode. The dataset comprises spatial projections, each comprising images of a biological sample. Each image includes a corresponding plurality of discrete attribute values for the probe spots. Each such value is associated with a probe spot in the plurality of probes spots based on the probe spot barcodes. The dataset is clustered using the discrete attribute values, or dimension reduction components thereof, for a plurality of loci at each respective probe spot across the images of the projections thereby assigning each probe spot to a cluster in a plurality of clusters. Morphological patterns are identified from the spatial arrangement of the probe spots in the various clusters.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting a neural network with additional operations. One of the methods includes maintaining, by a computational graph system that manages execution of computational graphs representing neural network operations for users of the computational graph system, data specifying a plurality of pre-trained neural networks, wherein each of the pre-trained neural networks is a neural network that has been trained on training data to determine trained values of the respective parameters of the neural network; obtaining data specifying a user computational graph representing neural network operations, the user computational graph comprising a plurality of nodes connected by edges; identifying (i) an insertion point after a first node in the user computational graph and (ii) a particular pre-trained neural network from the plurality of pre-trained neural networks; and inserting a remote call node into the user computational graph.

The present invention discloses a new method for analyzing, modifying, and distributing digital images and video in a quick, efficient, practical and/or cost-effective way. The method of processing video can take a different region or object and replace the pixels in the frames of the scenes that comprise the features and characteristics of the identified region or object with a different set of pixels. The replacement or other customizations of the frames and scenes lead to a naturally integrated video or image which is indistinguishable by the human eye or other visual system. In one embodiment, this invention can be used to provide different advertising elements into an image or set of images for different viewers, or to enable a viewer to control elements within a video and add their own preference or other elements.

An information processing apparatus obtains a plurality of attribute datasets including a subject attribute dataset, which are each a combination of a plurality of item values, and information indicating an area range that is taken as a target in a dimensional space. The information processing apparatus then performs a determination process of determining a change-target item value to be changed from among the plurality of item values of the subject attribute dataset and a changing direction for the change-target item value on the basis of the distribution of at least some of the plurality of attribute datasets in the dimensional space. The information processing apparatus outputs information indicating a result of changes made by alternately iterating a changing process of changing the change-target item value and the determination process that follows the changing process until the subject attribute dataset is within the area range.

An information processing apparatus obtains a plurality of attribute datasets including a subject attribute dataset, which are each a combination of a plurality of item values, and information indicating an area range that is taken as a target in a dimensional space. The information processing apparatus then performs a determination process of determining a change-target item value to be changed from among the plurality of item values of the subject attribute dataset and a changing direction for the change-target item value on the basis of the distribution of at least some of the plurality of attribute datasets in the dimensional space. The information processing apparatus outputs information indicating a result of changes made by alternately iterating a changing process of changing the change-target item value and the determination process that follows the changing process until the subject attribute dataset is within the area range.

Training an ordinal mapping deep neural network (OMDNN) can include receiving multiple samples, each a computer-processable data structure corresponding to a real-world object and including a data element indicating one of n predefined classes to which each sample is linked. Each sample can be mapped by the OMDNN to sample points of a multidimensional space. The OMDNN can predicts the class of each sample based on an ordinal mapping. Parameters of the OMDNN can be iteratively adjusted in response to misclassifying one or more samples. Iteratively adjusting the parameters can be based on an expected loss determined by an ordinal mapping loss function that measures (a) distances between each sample point in the multidimensional space and each other sample point of the same class and (b) overlap between sample points of different classes.

Training an ordinal mapping deep neural network (OMDNN) can include receiving multiple samples, each a computer-processable data structure corresponding to a real-world object and including a data element indicating one of n predefined classes to which each sample is linked. Each sample can be mapped by the OMDNN to sample points of a multidimensional space. The OMDNN can predicts the class of each sample based on an ordinal mapping. Parameters of the OMDNN can be iteratively adjusted in response to misclassifying one or more samples. Iteratively adjusting the parameters can be based on an expected loss determined by an ordinal mapping loss function that measures (a) distances between each sample point in the multidimensional space and each other sample point of the same class and (b) overlap between sample points of different classes.

Described herein are techniques for using a graph neural network to encode online job postings as embeddings. First, an input graph is defined by processing one or more rules to discover edges that connect nodes in an input graph, where the nodes of the input graph represent job postings or standardized job attributes, and the edges are determined based on analyzing a log of user activity directed to online job postings. Next, a graph neural network (GNN) is trained based on an edge prediction task. Finally, once trained, the GNN is used to derive node embeddings for the nodes (e.g., job postings) of the input graph, and in some instances, new online job postings not represented in the original input graph.

A method includes: obtaining a plurality of clinical red blood cell images, dividing red blood cells of different shapes at different positions in each of the red blood cell images into a plurality of submasks, and synthesizing the submasks corresponding to each of the red blood cell images to generate one mask to obtain a plurality of masks corresponding to the red blood cell images; collecting shape data of a plurality of red blood cells from the masks to obtain a training data set, calculating a segmentation boundary of each red blood cell in the training data set, and establishing a red blood cell shape data set based on the segmentation boundary of each red blood cell; collecting distribution data of each red blood cell in the red blood cell shape data set; and synthesizing the red blood cell shape data set into a plurality of red blood cell images.