Patent · US Active

Training a document classification neural network

US10528866B1 · kind B1 · utility

17Cited by

1References

35Claims

0Family size

Assignee

Google LLC · US

Inventors

Andrew M. Dai · San Francisco, US
Quoc V. Le · Stanford, US

Key dates

Filing date	Sep 6, 2016
Grant date	Jan 7, 2020
Priority date	—
Expiry date	Apr 6, 2038

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/09
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a document classification neural network. One of the methods includes training an autoencoder neural network to autoencode input documents, wherein the autoencoder neural network comprises the one or more LSTM neural network layers and an autoencoder output layer, and wherein training the autoencoder neural network comprises determining pre-trained values of the parameters of the one or more LSTM neural network layers from initial values of the parameters of the one or more LSTM neural network layers; and training the document classification neural network on a plurality of training documents to determine trained values of the parameters of the one or more LSTM neural network layers from the pre-trained values of the parameters of the one or more LSTM neural network layers.

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