Abstract: Systems and methods for improving accuracy of machine-learning models are described herein. The system can obtain, by one or more computing devices, component data from a donor model. The donor model can be an online model. The component data can have a first embedding. The system can store the component data in a persistent database. The component data can be input data for a plurality of recipient models. The system can receive from the first recipient model of the plurality of recipient models, a first request for the first embedding. The system can transmit, from the persistent database to the first recipient model, the first embedding. The system can process, using the first recipient model, the first embedding to generate a first recipient output.

Abstract: According to various implementations, generally disclosed herein is a hybrid and hierarchical neural architecture search (NAS) approach. The approach includes performing a search space partitioning scheme to divide the search space into sub-search spaces. The approach further includes performing a first type of NAS, such as a Multi-trial NAS, to cover a search across the sub-search spaces. The approach also includes performing a second type of NAS, such as a One-Shot NAS, to cover each sub-search space. The approach further includes automatically stopping the second type of NAS based on one or more early stopping criteria.

Abstract: A user device receives audio data of a user reading aloud a displayed portion of an ebook, and converts a portion of the audio data to spoken-text data. The user device determines one or more similarity scores based on a comparison between the spoken-text data and text data associated with the displayed portion of the ebook, and ranks the one or more similarity scores to determine a reading location in the text data that corresponds to the spoken-text data. The user device determines a pronunciation score using the spoken-text data and pronunciation data associated with the text data at the reading location. The user device performs an action based in part on the reading location and the pronunciation score.

Abstract: A user device receives audio data of a user reading aloud a displayed portion of an ebook, and converts a portion of the audio data to spoken-text data. The user device determines one or more similarity scores based on a comparison between the spoken-text data and text data associated with the displayed portion of the ebook, and ranks the one or more similarity scores to determine a reading location in the text data that corresponds to the spoken-text data. The user device determines a pronunciation score using the spoken-text data and pronunciation data associated with the text data at the reading location. The user device performs an action based in part on the reading location and the pronunciation score.