Method for learning neuaral network and device thereof
AssigneeSamsung Electronics Co., Ltd.
InventorsByeoungsu KIM, Sangsoo KO, Kyoungyoung KIM, Sanghyuck HA
Life of this patent
Estimating the term…
Abstract
A method of operating a neural network device including a plurality of layers, includes receiving sensing data from at least one sensor, determining environmental information, based on the received sensing data, determining multiple layers corresponding to the determined environmental information, and dynamically reconstructing the neural network device by changing at least two layers, among the plurality of layers, to the determined multiple layers.
Claims25
A method of operating a neural network device including a plurality of layers, the method comprising:
- receiving sensing data from at least one sensor;
- determining environmental information, based on the received sensing data;
- determining multiple layers corresponding to the determined environmental information;
- and
- dynamically reconstructing the neural network device by changing at least two layers, among the plurality of layers, to the determined multiple layers.
(canceled)
A neural network device including a plurality of layers, the neural network device comprising:
- at least one sensor configured to obtain sensing data;
- and
- a processor configured to:
- determine environmental information, based on the obtained sensing data;
- determine multiple layers corresponding to the determined environmental information;
- and
- dynamically reconstruct the neural network device by changing at least two layers, among the plurality of layers, to the determined multiple layers.
(canceled)
(canceled)
(canceled)
(canceled)
A host vehicle device comprising:
- a neural network device comprising a plurality of layers;
- and
- a vehicle controller configured to control a host vehicle, based on an output of the neural network device,
- wherein the neural network device comprises:
- at least one sensor configured to obtain sensing data;
- and
- a processor configured to:
- determine environmental information, based on the obtained sensing data;
- determine multiple layers corresponding to the determined environmental information;
- and
- dynamically reconstruct the neural network device by changing at least two layers, among the plurality of layers, to the determined multiple layers.
Dependencies are inferred from the claim text.