CONVOLUTIONAL GATED RECURRENT NEURAL NETWORKS
First Claim
Patent Images
1. A system comprising:
- a convolutional gated recurrent neural network (CGRN) implemented by one or more computers, wherein the CGRN is configured to;
maintain a state that is a tensor having dimensions x by y by m, wherein x, y, and m are each greater than one,for each of a plurality of time steps, update a currently maintained state by processing the currently maintained state through a plurality of convolutional gates, andprocess the updated state after a last time step in the plurality of time steps through an output layer, wherein the output layer is configured to receive the updated state after the last time step in the plurality of time steps and to modify the updated state to generate a CGRN output.
2 Assignments
0 Petitions
Accused Products
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a convolutional gated recurrent neural network (CGRN). In one of the systems, the CGRN is configured to maintain a state that is a tensor having dimensions x by y by m, wherein x, y, and m are each greater than one, and for each of a plurality of time steps, update a currently maintained state by processing the currently maintained state through a plurality of convolutional gates.
14 Citations
20 Claims
-
1. A system comprising:
a convolutional gated recurrent neural network (CGRN) implemented by one or more computers, wherein the CGRN is configured to; maintain a state that is a tensor having dimensions x by y by m, wherein x, y, and m are each greater than one, for each of a plurality of time steps, update a currently maintained state by processing the currently maintained state through a plurality of convolutional gates, and process the updated state after a last time step in the plurality of time steps through an output layer, wherein the output layer is configured to receive the updated state after the last time step in the plurality of time steps and to modify the updated state to generate a CGRN output. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
8. One or more non-transitory computer storage media storing instructions that when executed by one or more computers cause the one or more computers to implement:
-
a convolutional gated recurrent neural network (CGRN) implemented by one or more computers, wherein the CGRN is configured to; maintain a state that is a tensor having dimensions x by y by m, wherein x, y, and m are each greater than one, for each of a plurality of time steps, update a currently maintained state by processing the currently maintained state through a plurality of convolutional gates, and process the updated state after a last time step in the plurality of time steps through an output layer, wherein the output layer is configured to receive the updated state after the last time step in the plurality of time steps and to modify the updated state to generate a CGRN output. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A method comprising:
-
receiving a system input; initializing a state using the system input, wherein the state is a tensor having dimensions x by y by m, wherein x, y, and m are each greater than one; and processing the initialized state using a convolutional gated recurrent neural network (CGRN) implemented by one or more computers, wherein the CGRN is configured to; for each of a plurality of time steps, update a currently maintained state by processing the currently maintained state through a plurality of convolutional gates, and process the updated state after a last time step in the plurality of time steps through an output layer, wherein the output layer is configured to receive the updated state after the last time step in the plurality of time steps and to modify the updated state to generate a CGRN output for the system input. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification