Back to results
US 12,484,035 B2Granted
Apparatus and method for deprecoding a signal for a machine learning model
AssigneeNokia Solutions and Networks Oy
InventorsWen Liang Qi, Chenhui Ye, Dani Johannes Korpi
Life of this patent
Estimating the term…
Abstract
An apparatus for a receiver is provided, said apparatus comprising means for receiving an input signal, based on a frequency domain signal, means for performing deprecoding on the received input signal and means for providing the deprecoded signal as an input for a machine learning model, wherein the output of the machine learning model is a likelihood ratio.
Claims20
An apparatus for a receiver, the apparatus comprising:
- a processor;
- and
- a memory storing instructions, which when executed by the processor, cause the apparatus to:
- receive an input signal, based on a frequency domain signal;
- provide the input signal to a first machine learning model for processing the input signal;
- perform deprecoding on the processed input signal output by the first machine learning model;
- provide the deprecoded signal as an input for a second machine learning model, wherein the output of the second machine learning model is a likelihood ratio.
4 more elements
A method comprising, at a receiver:
- receiving an input signal, based on a frequency domain signal;
- providing the input signal to a first machine learning model for processing the input signal;
- performing deprecoding on an output signal of the first machine learning model;
- and
- providing the deprecoded signal as an input for a second machine learning model, wherein the output of the second machine learning model is a likelihood ratio.
2 more elements
An apparatus comprising:
- at least one processor and at least one memory including a computer program code, the at least one memory and computer program code configured to, with the at least one processor, cause the apparatus at least to, at a receiver:
- receive an input signal, based on a frequency domain signal;
- provide the input signal to a first machine learning model for processing the input signal;
- perform deprecoding on an output of the first machine learning model;
- and
- provide the deprecoded signal as an input for a second machine learning model, wherein the output of the second machine learning model is a likelihood ratio.
3 more elements
Dependencies are inferred from the claim text.