Abstract: A computer-implemented method for generating a training dataset. The method comprises receiving content comprising one or more elements, generating an element representation for each of the one or more elements by processing the content and one or more user-generated primitive element representations, generating a synthetic user-generated representation of the one or more elements based upon the one or more user-generated primitive element representations and the layout of the one or more elements in the content, and generating the training dataset based upon the synthetic user-generated representation and the content.

Abstract: Systems and methods for editing and generating digital ink. The present technology may provide systems and methods for training a handwriting model to generate digital ink that is stylistically and visually consistent with an original handwriting input, but which incorporates one or more changes to the text of the original handwriting input. In some examples, training may be performed using training examples that include an original handwriting sample and an original label representing the sequence of characters in the original handwriting sample. In such a case, the original handwriting sample may be processed to generate a style vector that is randomly masked, and the handwriting model may then be trained to generate a predicted handwriting sample that closely matches the original handwriting sample using the masked style vector and the original label as inputs.

Abstract: HET classifiers, which learn a multivariate Gaussian distribution over prediction logits, perform well on image classification problems with hundreds to thousands of classes. However, compared to standard classifiers (e.g., deterministic (DET) classifiers), they introduce extra parameters that scale linearly with the number of classes. This makes them infeasible to apply to larger-scale problems. In addition, HET classifiers introduce a temperature hyperparameter, which is ordinarily tuned. HET classifiers are disclosed, where the parameter count (when compared to a DET classifier) scales independently of the number of classes. In large-scale settings of the embodiments, the need to tune the temperature hyperparameter is removed, by directly learning it on the training data.

Abstract: Systems and methods for editing and generating digital ink. The present technology may provide systems and methods for training a handwriting model to generate digital ink that is stylistically and visually consistent with an original handwriting input, but which incorporates one or more changes to the text of the original handwriting input. In some examples, training may be performed using training examples that include an original handwriting sample and an original label representing the sequence of characters in the original handwriting sample. In such a case, the original handwriting sample may be processed to generate a style vector that is randomly masked, and the handwriting model may then be trained to generate a predicted handwriting sample that closely matches the original handwriting sample using the masked style vector and the original label as inputs.

Abstract: Systems and methods for editing and generating digital ink. The present technology may provide systems and methods for training a handwriting model to generate digital ink that is stylistically and visually consistent with an original handwriting input, but which incorporates one or more changes to the text of the original handwriting input. In some examples, training may be performed using training examples that include an original handwriting sample and an original label representing the sequence of characters in the original handwriting sample. In such a case, the original handwriting sample may be processed to generate a style vector that is randomly masked, and the handwriting model may then be trained to generate a predicted handwriting sample that closely matches the original handwriting sample using the masked style vector and the original label as inputs.

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: 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: Systems and methods for editing and generating digital ink. The present technology may provide systems and methods for training a handwriting model to generate digital ink that is stylistically and visually consistent with an original handwriting input, but which incorporates one or more changes to the text of the original handwriting input. In some examples, training may be performed using training examples that include an original handwriting sample and an original label representing the sequence of characters in the original handwriting sample. In such a case, the original handwriting sample may be processed to generate a style vector that is randomly masked, and the handwriting model may then be trained to generate a predicted handwriting sample that closely matches the original handwriting sample using the masked style vector and the original label as inputs.

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 computer-implemented method includes receiving a first visual media article from an entity that provides content sources, identifying a first content item of the first visual media article, and identifying in a database a second visual media article that includes a second content item, wherein the second content item is substantially similar to the first content item. The method further includes extracting from logging data one or more keywords that yield a listing of a content source that includes the second visual media article, and suggesting the extracted one or more keywords to the entity.

Abstract: Techniques are shown for predicting the number of times a media selection will be consumed by one or more users at a target time. Examples of user behavior during the consumption of a media selection are chosen as input features. A partitioner separates a set of media selections into a training subset and an evaluation subset. The input features are transformed into feature vectors, and a learned function is derived to define a relationship between the feature vector for the training subset and the number of times a media selection from the training subset is consumed. The learned function is then applied to a feature vector for the evaluation subset to test its accuracy.

Abstract: Described herein are techniques related to prediction of video revenue for non-monetized videos. This Abstract is submitted with the understanding that it will not be used to interpret or limit the scope and meaning of the claims. A video-revenue prediction tool predicts revenue for non-monetized videos using historical revenue data of monetized videos.

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: Photographic images can be used to enhance three-dimensional (3D) virtual models of a physical location. In an embodiment, a method of generating a 3D scene geometry includes obtaining a first plurality of images and corresponding distance measurements for a first vehicle trajectory; obtaining a second plurality of images and corresponding distance measurements for a second vehicle trajectory, the second vehicle trajectory intersecting the first vehicle trajectory; registering a relative vehicle position and orientation for one or more segments of each of a first vehicle trajectory and a second vehicle trajectory; generating a three-dimensional geometry for each vehicle trajectory; mapping the three-dimensional geometries for each vehicle trajectory onto a common reference system based on the registering; and merging the three-dimensional geometries from both trajectories to generate a complete scene geometry.