Machine learning for reliable communication under coarse quantization

This thesis addresses the use of machine learning methods for reliable transmission despite coarsely quantized soft information at the receiver. In particular, the design of powerful error correction algorithms under coarse quantization is presented. This requires an interdisciplinary approach based on the interplay of information theory, machine learning, and communications engineering. A particular focus is put on
the information bottleneck method. Interestingly, the designed coarsely quantized signal processing units achieve almost the same performance in terms of reliability as conventional non-quantized methods.

Subjects

Machine learning (ML)

Information theory

information bottleneck method

quantization

probabilistic modelling

channel coding

DDC Class

620: Ingenieurwissenschaften

Lizenz

https://creativecommons.org/licenses/by/4.0/

Name

Maximilian_Stark_PhD_thesis_Machine-Learning-for-Reliable-Communication-Under-Coarse-Quantization_tub.pdf

Size

2.63 MB

Format

Adobe PDF

Options

Machine learning for reliable communication under coarse quantization