Invention Grant
- Patent Title: Quasi-recurrent neural network based encoder-decoder model
-
Application No.: US15420801Application Date: 2017-01-31
-
Publication No.: US11080595B2Publication Date: 2021-08-03
- Inventor: James Bradbury , Stephen Joseph Merity , Caiming Xiong , Richard Socher
- Applicant: salesforce.com, inc.
- Applicant Address: US CA San Francisco
- Assignee: salesforce.com, inc.
- Current Assignee: salesforce.com, inc.
- Current Assignee Address: US CA San Francisco
- Agency: Haynes and Boone, LLP
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06N3/08 ; G06F40/30 ; G06F40/44 ; G06F40/216 ; G06F17/16 ; G06N3/10 ; G10L15/16 ; G10L15/18 ; G10L25/30 ; G06F40/00
Abstract:
The technology disclosed provides a quasi-recurrent neural network (QRNN) encoder-decoder model that alternates convolutional layers, which apply in parallel across timesteps, and minimalist recurrent pooling layers that apply in parallel across feature dimensions.
Public/Granted literature
- US20180129931A1 QUASI-RECURRENT NEURAL NETWORK BASED ENCODER-DECODER MODEL Public/Granted day:2018-05-10
Information query
