Recurrent encoder and decoder
AssigneeAmerican Software Safety Reliability Company
InventorBlake Rainwater
Life of this patent
Estimating the term…
Abstract
An encoder and decoder for translating sequential data into a fixed dimensional vector are created by applying an encoding-trainer input vector set as input to an encoding neural network to generate an encoding-trainer output vector set. One vector of the encoding-trainer output vector set is selected and a decoding-trainer input vector set is generated from it. A decoding neural network is trained by applying the generated decoding-trainer input vector set to the decoding neural network. The encoder and decoder can be used in implementations processing sequential data.
Claims20
A method for translating between a first context and a second context comprising:
- encoding source data of the first context using an encoding neural network to create an encoded input fixed dimensional vector representation of the source data;
- applying the encoded input fixed dimensional vector as input to a translator neural network trained to generate an output encoded fixed dimensional vector representation of target data of the second context, wherein the first context and second context differ;
- and
- decoding the output encoded fixed dimensional vector representation using a decoding neural network to recreate the target data,
- wherein the decoding neural network has been trained by applying a plurality of encoded fixed dimensional vectors representing sequential data encoded from a second data corpus of the second context as input to the decoding neural network.
A system for translating between a first context and a second context comprising:
- one or more processors;
- and
- one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform actions comprising:
- encoding source data of the first context using an encoding neural network to create an encoded input fixed dimensional vector representation of the source data;
- applying the encoded input fixed dimensional vector as input to a translator neural network trained to generate an output encoded fixed dimensional vector representation of target data of the second context, wherein the first context and second context differ;
- and
- decoding the output encoded fixed dimensional vector representation using a decoding neural network to recreate the target data,
- wherein the decoding neural network has been trained by applying a plurality of encoded fixed dimensional vectors representing sequential data encoded from a second data corpus of the second context as input to the decoding neural network.
A non-transitory computer readable medium storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform actions comprising:
- encoding source data of a first context using an encoding neural network to create an encoded input fixed dimensional vector representation of the source data;
- applying the encoded input fixed dimensional vector as input to a translator neural network trained to generate an output encoded fixed dimensional vector representation of target data of a second context, wherein the first context and second context differ;
- and
- decoding the output encoded fixed dimensional vector representation using a decoding neural network to recreate the target data,
- wherein the decoding neural network has been trained by applying a plurality of encoded fixed dimensional vectors representing sequential data encoded from a second data corpus of the second context as input to the decoding neural network.
Dependencies are inferred from the claim text.