# US 2022/0286181 A1 · Signal demapping

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0286181 A1
- Document ID: US20220286181A1
- Status: Published application
- Kind: A1
- Application number: 17/628,372
- Filed: 2019-09-03
- Published: 2022-09-08
- Earliest claimed: 2019-09-03
- Assignees: Nokia Technologies Oy
- Applicants: Nokia Technologies OY
- Inventors: Faycal AIT AOUDIA; Jakob HOYDIS
- Web page: https://patentgrep.com/patent/US20220286181A1

## CPC

- H04B 7/0639: {Using selective indices, e.g. of a codebook, e.g. pre-distortion matrix index [PMI] or for beam selection}
- G06N 3/045: Combinations of networks
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- H04B 7/0663: {using vector or matrix manipulations}
- G06N 3/063: using electronic means
- H04B: TRANSMISSION
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In one embodiment, a trainable logic includes determination logic configured to determine a plurality of available receiver configurations and associate each receiver configuration with a context matrix; codebook logic configured to select a quantisation codebook to be used by the trainable logic for the context matrices; and learning logic configured to learn from a training dataset including a plurality of received signal samples relevant to reconstruction of a transmitted message. The learning logic is configured to generate, from the training dataset, a set of superposed parameters and context matrices corresponding to the plurality of available receiver configurations and a set of contextual parameters for each context; quantize the context matrices according to the quantisation codebook; and repeat the generation of superposed parameters, context matrices and quantization of context matrices until a stop criterion is met.

## Claims

### Claim 1

An apparatus comprising:
trainable logic configured to quantize a plurality of receiver configurations said trainable logic including,
determination logic configured to determine a plurality of available receiver configurations and associate each receiver configuration with a context matrix;
codebook logic configured to select a quantisation codebook to be used by the trainable logic for the context matrices;
learning logic configured to learn from a training dataset comprising a plurality of received signal samples relevant to reconstruction of a transmitted message;
said learning logic being configured to,
generate, from the training dataset, a set of superposed parameters and context matrices corresponding to the plurality of available receiver configurations and a set of contextual parameters for each context, the contextual parameters being generatable from the superposed parameters by combination with the context matrix associated with each receiver configuration;
quantize the context matrices according to the quantisation codebook; and
repeat the generation of superposed parameters, context matrices and quantization of context matrices until a stop criterion is met.

### Claim 2 (depends on 1)

An apparatus according to claim 1, wherein the stopping criterion comprises one or more of a predefined number of iterations or meeting a predetermined performance metric.

### Claim 3 (depends on 1)

An apparatus according to claim 1, wherein the stopping criterion relates to a performance metric associated with the reconstruction of the transmitted message.

### Claim 4 (depends on 1)

An apparatus according to claim 1, wherein the stopping criterion relates to a performance metric associated with quantizing the context matrices according to the quantisation codebook.

### Claim 5 (depends on 1)

An apparatus according to claim 1, wherein selecting the quantisation codebook comprises:
setting coefficients of the context matrices to match values of a finite matrix codebook.

### Claim 6 (depends on 5)

An apparatus according to claim 5, wherein the finite matrix codebook comprises one of: {−1, 0, 1}, or values which are powers of two.

### Claim 7 (depends on 1)

An apparatus according to claim 1, wherein the combination of superposed parameters with the context matrix comprises one of matrix multiplication or element-wise product.

### Claim 8 (depends on 1)

An apparatus according to claim 1, wherein the receiver configurations comprise one or more of* a receiver or demodulation configuration.

### Claim 9 (depends on 1)

A device comprising:
reception logic configured to receive a wireless communication signal;
processing logic configured to process the received wireless communication signal and demap the received signal, said processing logic including the apparatus according to claim 1,

### Claim 10 (depends on 9)

A device according to claim 9, further comprising: receiver configuration selection logic configured to select a receiver configuration from said plurality of receiver configurations to apply to said received wireless communication system, based upon one or more factors including said generated superposed parameters and quantized context matrices.

### Claim 11

A method comprising:
quantising a plurality of receiver configurations by:
determining a plurality of available receiver configurations and associating each receiver configuration with a context matrix;
selecting a quantisation codebook to be used for the context matrices;
providing a training dataset comprising a plurality of received signal samples relevant to reconstruction of a transmitted message;
generating, from the training dataset a set of superposed parameters and context matrices corresponding to the plurality of available receiver configurations and a set of contextual parameters for each context, the contextual parameters being generatable from the superposed parameters by combination with the context matrix associated with each receiver configuration;
quantizing the context matrices according to the quantisation codebook and repeating the generating of superposed parameters, context matrices and quantisation of context matrices until a stop criterion is met.

### Claim 12 (depends on 11)

A non transitory computer readable medium storing instructions, which when executed by a processor, cause an apparatus including the processor to perform the method of claim 11.
