Abstract: Systems and methods for flexible parameter sharing for multi-task learning are provided. A training method can include obtaining a test input, selecting a particular task from one or more tasks, and training a multi-task machine-learned model for the particular task by performing a forward pass using the test input and one or more connection probability matrices to generate a sample distribution of test outputs, training the components of the machine-learned model based at least in part on the sample distribution, and performing a backwards pass to train a connection probability matrix of the multi-task machine-learned model using a straight-through Gumbel-softmax approximation.

Abstract: A method of determining a final architecture for a task neural network for performing a target machine learning task is described. The target machine learning task is associated with a target training dataset.

Abstract: Systems and methods for flexible parameter sharing for multi-task learning are provided. A training method can include obtaining a test input, selecting a particular task from one or more tasks, and training a multi-task machine-learned model for the particular task by performing a forward pass using the test input and one or more connection probability matrices to generate a sample distribution of test outputs, training the components of the machine-learned model based at least in part on the sample distribution, and performing a backwards pass to train a connection probability matrix of the multi-task machine-learned model using a straight-through Gumbel-softmax approximation.

Abstract: A system and method for automatic audience creation by scoring users of a content sharing service is provided. The system includes a user analysis module to monitor data associated with the users of the content sharing service; and a channel analysis module to monitor data associated with a first channel; a scoring module to score, based on the monitored data associated with users and the first channel, each user based on a ratio of views versus accesses for shared content sourced from the first channel; and an audience assignment module to create an audience for the first channel of users with scores above a predetermined threshold.

Abstract: A method for speech recognition, the method includes: extracting time-frequency speech features from a series of reference speech elements in a first series of sampling windows; aligning reference speech elements that are not of equal time span duration; constructing a common subspace for the aligned speech features; determining a first set of coefficient vectors; extracting a time-frequency feature image from a test speech stream spanned by a second sampling window; approximating the extracted image in the common subspace for the aligned extracted time-frequency speech features with a second coefficient vector; computing a similarity measure between the first and the second coefficient vector; determining if the similarity measure is below a predefined threshold; and wherein a match between the reference speech elements and a portion of the test speech stream is made in response to a similarity measure below a predefined threshold.

Abstract: A system for creating audiences for a shared content publisher, includes a data store comprising a computer readable medium storing a program of instructions for audiences for a shared content publisher; a processor that executes the program of instructions; a data processor to monitor access to an Internet web site by a first set of users for a reference time period; a window extraction module, based on a reference split period, to divide the monitored access into a vector X and a vector Y, wherein vector X is defined by accesses by the first set of users before the reference split period, and vector Y is defined by accesses by the first user after the reference split period; and a data analysis module to create a model based on the vector X and the vector Y, to evaluate the model based on a second set of users accessing content similar to vector X, to create a final model based on the evaluation, and to score a group of users associated with the shared content publisher based on the final model, the data pr

Abstract: A method for speech recognition, the method includes: extracting time—frequency speech features from a series of reference speech elements in a first series of sampling windows; aligning reference speech elements that are not of equal time span duration; constructing a common subspace for the aligned speech features; determining a first set of coefficient vectors; extracting a time—frequency feature image from a test speech stream spanned by a second sampling window; approximating the extracted image in the common subspace for the aligned extracted time—frequency speech features with a second coefficient vector; computing a similarity measure between the first and the second coefficient vector; determining if the similarity measure is below a predefined threshold; and wherein a match between the reference speech elements and a portion of the test speech stream is made in response to a similarity measure below a predefined threshold.