Systems and methods for implementing federated learning engine for integration of vertical and horizontal AI are disclosed herein. A method can include receiving a global model from a central aggregator communicatingly connected with a plurality of user environments, which global model including a plurality of layers. The method can include training a mini model on top of the global model with data gathered within the user environment, uploading the at least a portion of the mini model to the central aggregator, receiving a plurality of mini models, and creating a fusion model based on the received plurality of mini models.

According to a general aspect, a method can include receiving a photo of a virtual conference participant, and a depth map based on the photo, and generating a plurality of synthesized images based on the photo. The plurality of synthesized images can have respective simulated gaze directions of the virtual conference participant. The method can also include receiving, during a virtual conference, an indication of a current gaze direction of the virtual conference participant. The method can further include animating, in a display of the virtual conference, an avatar corresponding with the virtual conference participant. The avatar can be based on the photo. Animating the avatar can be based on the photo, the depth map and at least one synthesized image of the plurality of synthesized images, the at least one synthesized image corresponding with the current gaze direction.

According to a general aspect, a method can include receiving a photo of a virtual conference participant, and a depth map based on the photo, and generating a plurality of synthesized images based on the photo. The plurality of synthesized images can have respective simulated gaze directions of the virtual conference participant. The method can also include receiving, during a virtual conference, an indication of a current gaze direction of the virtual conference participant. The method can further include animating, in a display of the virtual conference, an avatar corresponding with the virtual conference participant. The avatar can be based on the photo. Animating the avatar can be based on the photo, the depth map and at least one synthesized image of the plurality of synthesized images, the at least one synthesized image corresponding with the current gaze direction.

Machine learning techniques are used, in one embodiment, to mitigate multipath in an L5 GNSS receiver. In one embodiment, training data is generated to provide ground truth data for excess path length (EPL) corrections for a set of received GNSS signals. A system extracts features from the set of received GNSS signals and uses the extracted features and the ground truth data to train a set of one or more neural networks that can produce EPL corrections for pseudorange measurements. The trained set of one or more neural networks can be deployed in GNSS receivers and used in the GNSS receivers to correct pseudorange measurements using EPL corrections provided by the trained set of neural networks.

Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training a machine-learning model for predicting event tags. The system obtains asset data for an electric power distribution system in a geographic area. The asset data includes: for each of a plurality of electrical assets of the electrical power distribution system, data indicating one or more characteristics of the electrical asset. The system further obtains sensor data for the electric power distribution system. The sensor data includes measurement data from a plurality of electric sensors. The system generates, by processing the asset data and the sensor data, partition data that includes, for each of the plurality of electrical assets, an assignment that assigns the electrical asset to one of a set of feeder networks.

A system for determining relevance of a light source to an automobile includes at least one camera adapted to capture images of light sources in proximity to the automobile, a controller in communication with the at least one camera and adapted to receive captured images from the at least one camera, the controller further adapted to estimate an orientation of at least one light source relative to the automobile, classify the at least one light source as one of relevant and irrelevant, and, when the at least one light source is classified as relevant, send information about the at least one light source to a planning module for the automobile.

A system for determining relevance of a light source to an automobile includes at least one camera adapted to capture images of light sources in proximity to the automobile, a controller in communication with the at least one camera and adapted to receive captured images from the at least one camera, the controller further adapted to estimate an orientation of at least one light source relative to the automobile, classify the at least one light source as one of relevant and irrelevant, and, when the at least one light source is classified as relevant, send information about the at least one light source to a planning module for the automobile.

The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating topic divergence classifications for digital videos based on words from the digital videos and further based on a digital text corpus representing a target topic. Particularly, the disclosed systems utilize a topic-specific knowledge encoder neural network to generate a topic divergence classification for a digital video to indicate whether or not the digital video diverges from a target topic. In some embodiments, the disclosed systems determine topic divergence classifications contemporaneously in real time for livestream digital videos or for stored digital videos (e.g., digital video tutorials). For instance, to generate a topic divergence classification, the disclosed systems generate and compare contextualized feature vectors from digital videos with corpus embeddings from a digital text corpus representing a target topic utilizing a topic-specific knowledge encoder neural network.

The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating topic divergence classifications for digital videos based on words from the digital videos and further based on a digital text corpus representing a target topic. Particularly, the disclosed systems utilize a topic-specific knowledge encoder neural network to generate a topic divergence classification for a digital video to indicate whether or not the digital video diverges from a target topic. In some embodiments, the disclosed systems determine topic divergence classifications contemporaneously in real time for livestream digital videos or for stored digital videos (e.g., digital video tutorials). For instance, to generate a topic divergence classification, the disclosed systems generate and compare contextualized feature vectors from digital videos with corpus embeddings from a digital text corpus representing a target topic utilizing a topic-specific knowledge encoder neural network.

A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.