Invention Grant
- Patent Title: Recurrent neural networks for data item generation
-
Application No.: US15016160Application Date: 2016-02-04
-
Publication No.: US11080587B2Publication Date: 2021-08-03
- Inventor: Karol Gregor , Ivo Danihelka
- Applicant: DeepMind Technologies Limited
- Applicant Address: GB London
- Assignee: DeepMind Technologies Limited
- Current Assignee: DeepMind Technologies Limited
- Current Assignee Address: GB London
- Agency: Fish & Richardson P.C.
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G10L25/30 ; G10L13/02

Abstract:
Methods, and systems, including computer programs encoded on computer storage media for generating data items. A method includes reading a glimpse from a data item using a decoder hidden state vector of a decoder for a preceding time step, providing, as input to a encoder, the glimpse and decoder hidden state vector for the preceding time step for processing, receiving, as output from the encoder, a generated encoder hidden state vector for the time step, generating a decoder input from the generated encoder hidden state vector, providing the decoder input to the decoder for processing, receiving, as output from the decoder, a generated a decoder hidden state vector for the time step, generating a neural network output update from the decoder hidden state vector for the time step, and combining the neural network output update with a current neural network output to generate an updated neural network output.
Public/Granted literature
- US20160232440A1 RECURRENT NEURAL NETWORKS FOR DATA ITEM GENERATION Public/Granted day:2016-08-11
Information query