Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a convolutional neural network using a regularization scheme. One of the methods includes repeatedly performing the following operations: obtaining a kernel of a particular convolutional layer; applying a Fourier transform to the kernel; generating a decomposition using singular-value decomposition (SVD); generating a regularized diagonal matrix; generating a recomposition; applying an inverse Fourier transform to the recomposition; and training the convolutional neural network on training inputs.

A method of building a model for estimating a level of psychological safety includes acquiring, by a computer, post data communicated between members in a team, identifying fixed type post data that does not contribute to evaluation of the psychological safety among the acquired post data, and creating the model based on content of the acquired post data from which the fixed type post data has been removed.

A system for rideshare matching using locality sensitive hashing is disclosed, including at least one rider device and at least one driver device in operable connection with a network. A rideshare application is in operable communication with the network and configured for matching a driver to a rider within a match pool via an artificial intelligence engine operating a locality sensitive hashing module.

A computer-implemented method for training a normalizing flow. The normalizing flow is configured to determine a first output signal characterizing a likelihood or a log-likelihood of an input signal. The normalizing flow includes at least one first layer which includes trainable parameters. A layer input to the first layer is based on the input signal and the first output signal is based on a layer output of the first layer. The training includes: determining at least one training input signal; determining a training output signal for each training input signal using the normalizing flow; determining a first loss value which is based on a likelihood or a log-likelihood of the at least one determined training output signal with respect to a predefined probability distribution; determining an approximation of a gradient of the trainable parameters; updating the trainable parameters of the first layer based on the approximation of the gradient.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a convolutional neural network using a regularization scheme. One of the methods includes repeatedly performing the following operations: obtaining a kernel of a particular convolutional layer; applying a Fourier transform to the kernel; generating a decomposition using singular-value decomposition (SVD); generating a regularized diagonal matrix; generating a recomposition; applying an inverse Fourier transform to the recomposition; and training the convolutional neural network on training inputs.

Systems, methods, apparatuses and devices for detecting facial expressions according to EMG signals for a virtual and/or augmented reality (VR/AR) environment, in combination with a system for simultaneous location and mapping (SLAM), are presented herein.

A method and a system for data imputation and classification are provided. The system includes a database, a historical sample imputation module and a current sample imputation and classification module. In the method, at first, an imputation calculation is performed on each of classified historical sample groups to obtain a basis matrix and a missing value corresponding to each of the classified historical sample groups. Thereafter, a sample classification stage is performed. In the sample classification stage, an IPP (Iterative Projection Pursuit) algorithm and an equation of nonlinear inequality constraints to calculate weighting vectors corresponding to a current sample. Thereafter, plural candidate samples corresponding to different classes are calculated in accordance with the basis matrix and the weighting vectors, and the sample class of the current sample and a prediction value for a missing value of the current sample are determined accordingly.

Systems, methods, apparatuses and devices for detecting facial expressions according to EMG signals for a virtual and/or augmented reality (VR/AR) environment, in combination with a system for simultaneous location and mapping (SLAM), are presented herein.

One embodiment provides a method and system which facilitates optimizing a pair of affine classifiers based on a diversity metric. During operation, the system defines a diversity metric based on an angle between decision boundaries of a pair of affine classifiers. The system includes the diversity metric as a regularization term in a loss function optimization for designing the pair of affine classifiers, wherein the designed pair of affine classifiers are mutually orthogonal. The system predicts an outcome for a testing data object based on the designed pair of mutually orthogonal affine classifiers.

Various embodiments of the present invention disclose techniques for implementing an automatic data processing scheme for evaluating robust data sets to optimize procedure efficiency. A method may include determining a weighting-based input data object parameter for a robust data set; determining a variance-based input data object cohort parameter for a subset of the robust data set; generating a predictive variance metric for a data object of the subset based at least in part on the variance-based input data object cohort parameter and a first predictive metric attribute for the data object; generating a predictive weighting metric for the data object based at least in part on the weighting-based input data object parameter and a second predictive metric attribute for the data object; and generating a predictive metric data object for evaluating the robust data set based at least in part on the predictive variance metric and the predictive weighting metric.