The present disclosure relates generally to machine learning. More particularly, the present disclosure relates to systems and methods that regularize neural networks by decorrelating neurons or other parameters of the neural networks during training of the neural networks promoting these parameter to innovate over one another.

A multi-task relationship learning system 80 for simultaneously estimating a plurality of prediction models includes a learner 81 for optimizing the prediction models so as to minimize a function that includes a sum total of errors indicating consistency with data and a regularization term deriving sparsity relating to differences between the prediction models, to estimate the prediction models.

A local connectivity feature transform (LCFT) is applied to binary document images containing text characters, to generate transformed document images which are then input into a bi-directional Long Short Term Memory (LSTM) neural network to perform character/word recognition. The LCFT transformed image is a gray scale image where the pixel values encode local pixel connectivity information of corresponding pixels in the original binary image. The transform is one that provides a unique transform score for every possible shape represented as a 33 block. In one example, the transform is computed using a 33 weight matrix that combines bit coding with a zigzag pattern to assign weights to each element of the 33 block, and by summing up the weights for the non-zero elements of the 33 block shape.

The present application discloses a method, system, and computer system for building a model associated with a dataset. The method includes receiving a data set, the dataset comprising a plurality of keys and a plurality of key-value relationships, determining a plurality of models to build based at least in part on the dataset, wherein determining the plurality of models to build comprises using the dataset format information to identify the plurality of models, building the plurality of models, and optimizing at least one of the plurality of models.

An information processing system includes: an acquisition processing unit that acquires a plurality of pieces of data to be classified; a classification processing unit that classifies the plurality of pieces of data acquired by the acquisition processing circuit into a plurality of groups, extracts a feature element representing a feature of a group for each of the plurality of classified groups, and generates a classification map in which the feature element is displayed in association with the group; a reception processing unit that receives an operation of selecting the predetermined feature element in the classification map from a user; and an update processing unit that executes processing of changing the group based on the feature element selected by the user and updates the classification map.

The present disclosure refers to a method and a system of sudden water pollutant source detection by forward-inverse coupling, including: building an one-dimensional forward water quality simulation model of a river way according to acquired mechanical parameters and water quality parameters; according to the one-dimensional forward water quality simulation model of the river way, measuring and calculating each monitoring index by using an inverse optimization source-detection model; by constructing the one-dimensional forward water quality simulation model of the river way, using the inverse optimization source-detection model for measurement and calculation; and performing the Bayesian updating, in order to realize multi-information fusion. The present disclosure may reasonably control and use different observation information, and combine the redundancy or complementarity of multi-sourced information in space or in time to obtain consistent interpretation of the measured object, thus overcoming the uncertainty of the water environment, improving the accuracy of water pollutant source detection.

In an example, high-dimensional data is projected to a multi-dimensional space to differentiate clusters of the high-dimensional data. A user selection of at least two of the clusters may be received and a plurality of dissimilar dimensions may be extracted from the at least two clusters. In addition, a user selected of a dissimilar dimension from the plurality of extracted dissimilar dimensions may be received. In response to receipt of the user selection of the dissimilar dimension from the plurality of dissimilar dimensions, a plurality of correlated dimensions to the dissimilar dimension may be determined. In addition, the plurality of dissimilar dimensions and the plurality of correlated dimensions may be displayed.

Techniques are provided for training graph neural networks with heterophily datasets and generating predictions for such datasets with heterophily. A computing device receives a dataset including a graph data structure and processes the dataset using a graph neural network. The graph neural network defines prior belief vectors respectively corresponding to nodes of the graph data structure, executes a compatibility-guided propagation from the set of prior belief vectors and using a compatibility matrix. The graph neural network predicts predicting a class label for a node of the graph data structure based on the compatibility-guided propagations and a characteristic of at least one node within a neighborhood of the node. The computing device outputs the graph data structure where it is usable by a software tool for modifying an operation of a computing environment.

The present application discloses a method, system, and computer system for building a model associated with a dataset. The method includes receiving a data set, the dataset comprising a plurality of keys and a plurality of key-value relationships, determining a plurality of models to build based at least in part on the dataset, wherein determining the plurality of models to build comprises using the dataset format information to identify the plurality of models, building the plurality of models, and optimizing at least one of the plurality of models.

In an example, high-dimensional data is projected to a multi-dimensional space to differentiate clusters of the high-dimensional data. A user selection of at least two of the clusters may be received and a plurality of dissimilar dimensions may be extracted from the at least two clusters. In addition, a user selected of a dissimilar dimension from the plurality of extracted dissimilar dimensions may be received. In response to receipt of the user selection of the dissimilar dimension from the plurality of dissimilar dimensions, a plurality of correlated dimensions to the dissimilar dimension may be determined. In addition, the plurality of dissimilar dimensions and the plurality of correlated dimensions may be displayed.