System and method for deep memory network
AssigneeSamsung Electronics Co., Ltd.
InventorsYilin Shen, Yue Deng, Avik Ray, Hongxia Jin
Life of this patent
Estimating the term…
Abstract
An electronic device including a deep memory model includes at least one memory and at least one processor coupled to the at least one memory. The at least one processor is configured to receive input data to the deep memory model. The at least one processor is also configured to extract a history state of an external memory coupled to the deep memory model based on the input data. The at least one processor is further configured to update the history state of the external memory based on the input data. In addition, the at least one processor is configured to output a prediction based on the extracted history state of the external memory.
Claims27
A method for managing a deep memory model coupled to an external memory, the method comprising:
- receiving input data to the deep memory model;
- extracting a history state of the external memory based on the input data;
- updating the history state of the external memory based on the input data;
- and
- outputting a prediction based on the extracted history state of the external memory.
An electronic device including a deep memory model, the electronic device comprising:
- at least one memory;
- and
- at least one processor coupled to the at least one memory, the at least one processor configured to:
- receive input data to the deep memory model;
- extract a history state of an external memory coupled to the deep memory model based on the input data;
- update the history state of the external memory based on the input data;
- and
- output a prediction based on the extracted history state of the external memory.
A non-transitory computer readable medium embodying a computer program, the computer program comprising instructions that when executed cause at least one processor of an electronic device to:
- receive input data to a deep memory model;
- extract a history state of an external memory coupled to the deep memory model based on the input data;
- update the history state of the external memory based on the input data;
- and
- output a prediction based on the extracted history state of the external memory.
A method for training a deep memory model coupled to an external memory, the method comprising:
- selecting a data set from among a plurality of data sets;
- adding the selected data set to a training sample, wherein the training sample comprises a plurality of history states of the deep memory model;
- creating one or more mini-batches from the plurality of history states;
- training the deep memory model using the one or more mini-batches;
- and
- updating one or more parameters of the deep memory model.
Dependencies are inferred from the claim text.