Encoding method and neural network encoder structure usable in wireless communication system
AssigneeLG Electronics Inc.
InventorsBonghoe Kim, Jongwoong Shin, Byounghoon Kim
Life of this patent
Estimating the term…
Abstract
Provided are an encoding method performed by a neural network encoder in a wireless communication system and the neural network encoder. The method includes a first encoding step of encoding input data transmitted from a higher layer, an interleaving step of performing interleaving on a first output which is an output of the first encoding step and a second encoding step of encoding a second output which is an output obtained by interleaving the first output. Here, each of the first encoding step and the second encoding step is performed based on one or more neural networks.
Claims14
An encoding method performed by a neural network encoder in a user equipment (UE) in a wireless communication system, the method comprising:
- a first encoding step, by a first neural network, of encoding input data from a medium access control (MAC) layer, wherein the first neural network is an outer encoder;
- an interleaving step of performing interleaving on a first output of the first encoding step;
- a second encoding step, by a second neural network, of encoding a second output of the interleaving step, wherein the second neural network is an inner encoder;
- a normalization step of performing a normalization operation on an output of the inner encoder to control a divergence of values within the neural network encoder, wherein the normalization operation is based on a weighted sum of a current output and a previous output of the inner encoder;
- and
- a puncturing step of performing puncturing at an output of at least one of the outer encoder and the inner encoder to generate a specific code rate for data transmission,
- wherein the neural network encoder receives information on a parameter for the normalization operation for the first neural network and the second neural network from a base station.
A neural network encoder, the neural network encoder comprising:
- at least one memory storing instructions;
- at least one transceiver;
- and
- at least one processor coupling the at least one memory and the at least one transceiver, wherein the at least one processor is configured to execute the instructions,
- wherein the at least one processor performs is configured to perform:
- a first encoding step, by a first neural network, of encoding input data from a medium access control (MAC) layer, wherein the first neural network is an outer encoder;
- an interleaving step of performing interleaving on a first output of the first encoding step;
- a second encoding step, by a second neural network, of encoding a second output of the interleaving step, wherein the second neural network is an inner encoder;
- a normalization step of performing a normalization operation on an output of the inner encoder to control a divergence of values within the neural network encoder, wherein the normalization operation is based on a weighted sum of a current output and a previous output of the inner encoder;
- and
- a puncturing step of performing puncturing at an output of at least one of the outer encoder and the inner encoder to generate a specific code rate for data transmission,
- wherein the neural network encoder receives information on a parameter for the normalization operation for the first neural network and the second neural network from a base station.
An apparatus configured to control a neural network encoder, the apparatus comprising:
- at least one processor;
- and
- at least one memory executably coupled to the at least one processor and storing instructions,
- wherein the at least one processor is configured to execute the instructions,
- wherein the at least one processor is configured to perform:
- a first encoding step, by a first neural network, of encoding input data from a medium access control (MAC) layer, wherein the first neural network is an outer encoder;
- an interleaving step of performing interleaving on a first output of the first encoding step;
- a second encoding step, by a second neural network, of encoding a second output of the interleaving step, wherein the second neural network is an inner encoder;
- a normalization step of performing a normalization operation on an output of the inner encoder to control a divergence of values within the neural network encoder, wherein the normalization operation is based on a weighted sum of a current output and a previous output of the inner encoder;
- and
- a puncturing step of performing puncturing at an output of at least one of the outer encoder and the inner encoder to generate a specific code rate for data transmission,
- wherein the neural network encoder receives information on a parameter for the normalization operation for the first neural network and the second neural network from a base station.
Dependencies are inferred from the claim text.