In some embodiments, a method receives a first sequence of inputs for processing via a sub-model of a plurality of sub-model. The plurality of sub-models are part of a main model. An input in the sequence of inputs is masked with a masked value to generate a second sequence of inputs. The method processes the second sequence of inputs using the sub-model to generate a sequence of features that correspond to the second sequence of inputs and processes the sequence of features to generate a first output. The first output is processed to generate a second output of the main model. The sub-model is trained based on a feature in the sequence of features that corresponds to the masked input and the second output.

Techniques for generating distributed representations of computing processes and events are provided. According to one set of embodiments, a computer system can receive occurrence data pertaining to a plurality of computing processes and a plurality of events associated with the plurality of computing processes. The computer system can then generate, based on the occurrence data, (1) a set of distributed process representations that includes, for each computing process, a representation that encodes a sequence of events associated with the computing process in the occurrence data, and (2) a set of distributed event representations that includes, for each event, a representation that encodes one or more event properties associated with the event and one or more events that occur within a window of the event in the occurrence data.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing an input audio waveform using a generator neural network to generate an output audio waveform. In one aspect, a method comprises: receiving an input audio waveform; processing the input audio waveform using an encoder neural network to generate a set of feature vectors representing the input audio waveform; and processing the set of feature vectors representing the input audio waveform using a decoder neural network to generate an output audio waveform that comprises a respective output audio sample for each of a plurality of output time steps.

Systems/techniques that facilitate self-supervised deblurring are provided. In various embodiments, a system can access an input image generated by an imaging device. In various aspects, the system can train, in a self-supervised manner based on a point spread function of the imaging device, a machine learning model to deblur the input image. More specifically, the system can append to the model one or more non-trainable convolution layers having a blur kernel that is based on the point spread function of the imaging device. In various aspects, the system can feed the input image to the model, the model can generate a first output image based on the input image, the one or more non-trainable convolution layers can generate a second output image by convolving the first output image with the blur kernel, and the system can update parameters of the model based on a difference between the input image and the second output image.

Embodiments of the present disclosure provide systems and methods for training a machine-learning model for predicting emotions from received media data. Methods according to the present disclosure include displaying a user interface. The user interface includes a predefined media content, a plurality of predefined emotion tags, and a user interface control for controlling a recording of the user imitating the predefined media content. Methods can further include receiving, from a user, a selection of one or more emotion tags from the plurality of predefined emotion tags, receiving the recording of the user imitating the predefined media content, storing the recording in association with the selected one or more emotion tags, and training, based on the recording, the machine-learning model configured to receive input media data and predict an emotion based on the input media data.

A method for training a self-learning algorithm, where the algorithm is designed, as a function of one or more physical parameters of a technical device, to predict one or more values of one or more physical parameters of the device. The algorithm undergoes a basic training using values of the physical parameters that have been obtained by simulation of at least part of the device. The algorithm then undergoes build-up training with measured values of the physical parameters.

A method for training a self-learning algorithm, where the algorithm is designed, as a function of one or more physical parameters of a technical device, to predict one or more values of one or more physical parameters of the device. The algorithm undergoes a basic training using values of the physical parameters that have been obtained by simulation of at least part of the device. The algorithm then undergoes build-up training with measured values of the physical parameters.

An intelligent dog collar for monitoring physiological parameters of a dog, comprising: a movement sensor unit comprising an accelerometer and/or a gyrometer, wherein the movement sensor unit is configured to detect raw movement signals of the dog collar, a storage module storing a trained neural network, the neural network being configured to determine a physiologic information into raw movement signals detected by the movement sensor unit, a processing unit connected to the movement sensor unit and configured to operate the trained neural network, a memory configured to store the identified physiologic information, an interface for transmitting to a communication device the identified physiologic information.

A video generation method is provided. The video generation method includes: obtaining global semantic information and local semantic information of a text, where the local semantic information corresponds to a text fragment in the text, searching, based on the global semantic information, a database to obtain at least one first data corresponding to the global semantic information; searching, based on the local semantic information, the database to obtain at least one second data corresponding to the local semantic information; obtaining, based on the at least one first data and the at least one second data, a candidate data set; matching, based on a relevancy between each of at least one text fragment and corresponding candidate data in the candidate data set, target data for the at least one text fragment; and generating, based on the target data matched with each of the at least one text fragment, a video.

A video generation method is provided. The video generation method includes: obtaining global semantic information and local semantic information of a text, where the local semantic information corresponds to a text fragment in the text, searching, based on the global semantic information, a database to obtain at least one first data corresponding to the global semantic information; searching, based on the local semantic information, the database to obtain at least one second data corresponding to the local semantic information; obtaining, based on the at least one first data and the at least one second data, a candidate data set; matching, based on a relevancy between each of at least one text fragment and corresponding candidate data in the candidate data set, target data for the at least one text fragment; and generating, based on the target data matched with each of the at least one text fragment, a video.