Amazon Technologies, Inc.

Roshan Harish Makhijani

Vijai Mohan

Grant Michael Emery

Benjamin Thomas Cohen

Gaurav Chanda

Madhu Madhava Kurup

Soo-Min Pantel

Sanjeev Jain

Charles Lawrence Scott

Seong Jin Park

Brett Patrick Canfield

Alex Michael Shipman

Paul Phillip Mannino

Corey Lucius

Systems and methods are provided for rendering a first interface for presentation by a user computing device based on a first user input and information received over a network. The first interface can include item information. Additional item information may be stored at the user computing device at the time that the first interface is processed, but not initially displayed. Based on receiving a second user input, a second interface can be displayed that includes the additional item information, where the second interface may be displayed over a first portion of the first interface such that the first user interface remains accessible. The second interface may be populated with portions of the previously stored additional item information without necessarily obtaining further information over the network.

Caching item information for display in an interface overlay

The present disclosure is directed to filtering co-occurrence data. In one embodiment, a machine learning model can be trained. An output of an intermediate structure of the machine learning model (e.g., an output of an internal layer of a neural network) can be used as a representation of an event. Similarities between representations of events can be determined and used to generate, augment, or modify co-occurrence data.

Prediction filtering using intermediate model representations

Features are disclosed for identifying randomized latent feature language modeling, such as a recurrent neural network language modeling (RNNLM). Sequences of item identifiers may be provided as the language for training the language model where the item identifiers are the words of the language. To avoid localization bias, the sequences may be randomized prior to or during the training process to provide more accurate prediction models.

Randomized latent feature learning

Features are disclosed for identifying and routing items for tagging using a latent feature model, such as a recurrent neural network language model (RNNLM). The model may be trained to identify latent features for catalog items such as movies, books, food items, beverages, and the like. Based on similarities in latent features, tags previous assigned to items may be applied to untagged items. Application may be manual or automatic. In either case, resources need to be balances to ensure efficient tagging of items. The included features help to identify and direct these limited tagging resources.

Latent feature based tag routing

Growing community of inventors

Boston, MA, United States of America

Roshan Harish Makhijani