Patent · US Active

Training neural networks to generate structured embeddings

US11494695B2 · kind B2 · utility

0Cited by
1References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 27, 2019
Grant dateNov 8, 2022
Priority date
Expiry dateSep 28, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/048
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model to generate embeddings of inputs to the machine learning model, the machine learning model having an encoder that generates the embeddings from the inputs and a decoder that generates outputs from the generated embeddings, wherein the embedding is partitioned into a sequence of embedding partitions that each includes one or more dimensions of the embedding, the operations comprising: for a first embedding partition in the sequence of embedding partitions: performing initial training to train the encoder and a decoder replica corresponding to the first embedding partition; for each particular embedding partition that is after the first embedding partition in the sequence of embedding partitions: performing incremental training to train the encoder and a decoder replica corresponding to the particular partition.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.