Abstract: This document relates to automated generation of machine learning models, such as neural networks. One example system includes a hardware processing unit and a storage resource. The storage resource can store computer-readable instructions cause the hardware processing unit to perform an iterative model-growing process that involves modifying parent models to obtain child models. The iterative model-growing process can also include selecting candidate layers to include in the child models based at least on weights learned in an initialization process of the candidate layers. The system can also output a final model selected from the child models.

Abstract: This document relates to automated generation of machine learning models, such as neural networks. One example system includes a hardware processing unit and a storage resource. The storage resource can store computer-readable instructions cause the hardware processing unit to perform an iterative model-growing process that involves modifying parent models to obtain child models. The iterative model-growing process can also include selecting candidate layers to include in the child models based at least on weights learned in an initialization process of the candidate layers. The system can also output a final model selected from the child models.

Abstract: This document relates to automated generation of machine learning models, such as neural networks. One example system includes a hardware processing unit and a storage resource. The storage resource can store computer-readable instructions cause the hardware processing unit to perform an iterative model-growing process that involves modifying parent models to obtain child models. The iterative model-growing process can also include selecting candidate layers to include in the child models based at least on weights learned in an initialization process of the candidate layers. The system can also output a final model selected from the child models.

Abstract: A set of content items, such as web pages, are identified in response to a query generated by a user. The Identified content items are initially ranked using a ranking scheme. User-interaction data that describes preferences that the user may have towards some of the ranked content items is received. In order to personalize the ranking of the content items for the user, the user-interaction data is used to re-rank the ranked content items in a way that favors content items that are preferred by the user, while also preserving the initial broadly applicable ranking with respect to content items that are not preferred or that are equally preferred by the user.

Abstract: Various technologies pertaining to dynamically identifying travel segments to be taken by a traveler traveling in a region are described herein, where observations about travel segments in the region are sparse and subject to alteration. A computer-implemented graph can be loaded into a memory, where the computer-implemented graph is representative of the region. The computer-implemented graph includes nodes that represent locations in the region and edges that represent travel segments of the region, where the edges have costs assigned thereto, and further where there is a defined statistical relationship between the costs. When an observation about a travel path is received, using the computer-implemented graph, inferences can be made about costs of traversing other travel paths in the region.

Abstract: A set of content items, such as web pages, are identified in response to a query generated by a user. The Identified content items are initially ranked using a ranking scheme. User-interaction data that describes preferences that the user may have towards some of the ranked content items is received. In order to personalize the ranking of the content items for the user, the user-interaction data is used to re-rank the ranked content items in a way that favors content items that are preferred by the user, while also preserving the initial broadly applicable ranking with respect to content items that are not preferred or that are equally preferred by the user.

Abstract: Various technologies pertaining to dynamically identifying travel segments to be taken by a traveler traveling in a region are described herein, where observations about travel segments in the region are sparse and subject to alteration. A computer-implemented graph can be loaded into a memory, where the computer-implemented graph is representative of the region. The computer-implemented graph includes nodes that represent locations in the region and edges that represent travel segments of the region, where the edges have costs assigned thereto, and further where there is a defined statistical relationship between the costs. When an observation about a travel path is received, using the computer-implemented graph, inferences can be made about costs of traversing other travel paths in the region.

Abstract: Disclosed is a computer-assisted method for analyzing the surroundings of a display device. At least two different patterns are displayed successively on a display device connected to a computer. A camera is also connected to the computer and is directed towards objects in front of the display device. Each time a pattern is displayed on the display device, at least one image of the surroundings is captured. The captured images are combined to create a difference image. The difference image is analyzed to interpret the objects in the surroundings. For example, calculations may be performed to segment the foreground from the background of the surroundings or to estimate the range (distance) of the objects from the display device. An apparatus for performing this computer-assisted method is also disclosed.

Abstract: Neural network architectures are represented by symbol strings. An initial population of networks is trained and evaluated. The strings representing the fittest networks are modified according to a genetic algorithm and the process is repeated until an optimized network is produced.

Abstract: Neural network architectures are represented by symbol strings. An initial population of networks is trained and evaluated. The strings representing the fittest networks are modified according to a genetic algorithm and the process is repeated until an optimized network is produced.

Abstract: Disclosed is a computer-assisted method for analyzing the surroundings of a display device. At least two different patterns are displayed successively on a display device connected to a computer. A camera is also connected to the computer and is directed towards objects in front of the display device. Each time a pattern is displayed on the display device, at least one image of the surroundings is captured. The captured images are combined to create a difference image. The difference image is analyzed to interpret the objects in the surroundings. For example, calculations may be performed to segment the foreground from the background of the surroundings or to estimate the range (distance) of the objects from the display device. An apparatus for performing this computer-assisted method is also disclosed.

Abstract: A method for filling in missing attribute values in a data set array of cases and attribute positions includes the steps of, for a first case which includes an empty attribute position, determining a first set of K nearest neighbor cases which have known values for the corresponding attribute position as the empty attribute position in the first case; determining a filled in attribute value from the first set of K nearest neighbor cases for the empty attribute position of the first case; determining a second set of K nearest neighbor cases to the first case which have known values for the corresponding attribute position as the empty attribute position in the first case; and revising the filled in attribute value of the first case with an attribute value determined from the second set of K nearest neighbor cases. The revision process is typically repeated until the filled in values stop improving or until a preset limit on the number of iterations is reached.