Described are methods and systems are for generating dynamic conversational queries. For example, as opposed to being a simply reactive system, the methods and systems herein provide means for actively determining a user's intent and generating a dynamic query based on the determined user intent. Moreover, these methods and systems generate these queries in a conversational environment.

Intelligent analysis and prognosis-based data partitioning orchestration for optimizing database performance. Partitioning is not limited to partitioning keys established solely based on the columns of the table being partitioned, rather analysis is undertaken on dependent tables and the past behavior of fundamental data elements in the database is assessed as a means for determining the most optimal partitioning scheme. Thus, relevant information and values in the table being partitioned, as well as dependent tables and the fundamental data elements is used to determine how likely each record/row in the table is to be subjected to a data manipulation operation. The likelihood of a data manipulation operation being performed on each record serves as the basis for assigning the record to one of a plurality of partitions.

A method for generating a synthetic dataset from an original dataset includes encoding categorical features of the original dataset, embedding the encoded dataset in a low-dimensional space, selecting a seed record from the embedded dataset, identifying a plurality of nearest neighbor records to the seed record, generating a new record by randomly selecting features from the plurality of nearest neighbor records, and concatenating the new record into the synthetic dataset. For a synthetic dataset that contains N records, which may be the same as or different from the number of records in the original dataset, the selecting, identifying, generating, and concatenating operations operate a total of N times on the records in the embedded dataset.

A computer-implemented method for performing a classification of an input signal by a neural network includes: computing, by a feature extraction unit of the neural network, a D-dimensional query vector, wherein D is an integer; generating, by a classification unit of the neural network, a set of C fixed D-dimensional quasi-orthogonal bipolar vectors as a fixed classification matrix, wherein C is an integer corresponding to a number of classes of the classification unit; and performing a classification of a query vector based, at least in part, on the fixed classification matrix.

A computer-implemented method for performing a classification of an input signal by a neural network includes: computing, by a feature extraction unit of the neural network, a D-dimensional query vector, wherein D is an integer; generating, by a classification unit of the neural network, a set of C fixed D-dimensional quasi-orthogonal bipolar vectors as a fixed classification matrix, wherein C is an integer corresponding to a number of classes of the classification unit; and performing a classification of a query vector based, at least in part, on the fixed classification matrix.

Similarities between events that include a plurality of dimensions are computed, the similarities computed based on binary comparisons between the events and based on user-specified weights for the dimensions. Multidimensional scaling (MDS) values are calculated based on the computed similarities between the events. A graphical visualization is generated of a temporal plot of the events, the temporal plot comprising a first axis corresponding to time, and a second axis corresponding to the MDS values, and the temporal plot representing overlapping time slices each containing pixels representing a respective subset of the events.

A system method for occluding contour detection using a fully convolutional neural network is disclosed. A particular embodiment includes: receiving an input image; producing a feature map from the input image by semantic segmentation; learning an array of upscaling filters to upscale the feature map into a final dense feature map of a desired size; applying the array of upscaling filters to the feature map to produce contour information of objects and object instances detected in the input image; and applying the contour information onto the input image.

A system method for occluding contour detection using a fully convolutional neural network is disclosed. A particular embodiment includes: receiving an input image; producing a feature map from the input image by semantic segmentation; learning an array of upscaling filters to upscale the feature map into a final dense feature map of a desired size; applying the array of upscaling filters to the feature map to produce contour information of objects and object instances detected in the input image; and applying the contour information onto the input image.

Aspects of the present disclosure include methods, systems, and non-transitory computer readable media that perform the steps of receiving a first plurality of snapshots, generating a first plurality of descriptors each associated with the first plurality of snapshots, grouping the first plurality of snapshots into at least one cluster based on the plurality of descriptors, selecting a representative snapshot for each of the at least one cluster, generating at least one second descriptor for the representative snapshot for each of the at least one cluster, wherein the at least one second descriptor is more complex than the first plurality of descriptors, and identifying a target by applying the at least second descriptor to a second plurality of snapshots.

A state quantity prediction device includes: a first differential predictive value calculation unit configured to deal with a nonlinear component of a function whose variables are dynamic characteristics of the state quantity with respect to the input parameter and a difference value between a past predictive value of the state quantity and a predictive value of the physical model, input the input parameter and the past predictive value of the state quantity, and include a learned neutral network for outputting a first differential predictive value; a second differential predictive value calculation unit configured to deal with a linear component of the function, input the input parameter and the past predictive value, and output a second differential predictive value; and a state quantity predictive value calculation unit configured to calculate a predictive value of the state quantity.