It is expected that the demand for larger and larger data rates will continue to rise in the coming years with applications like smart sensor networks, distributed machine learning, digital twins of production facilities, etc. With the recent advances in machine learning techniques, semantic communication has been proposed a solution to push beyond the boundaries of conventional communication systems, as semantic communication does not require the accurate recovery of all information available at the sender, but rather the recovery of the meaning that the sender wants to convey with a specific task in mind.

As a example, the concept of semantic communication can outperform classical communication methods in a scenario, where each agent in a multi agent network observes some data with the goal of solving a task together. As a more specific example, in [1] each agent has one part of an image available, and the goal at the central receiver is to classify the whole image correctly. In the classical approach the image would be transmitted in its entirety, and the classification algorithm would use the received image as its input. However, it was shown that the data rate can be greatly reduced by using the semantic communication approach, where only the meaning of the content of each image part is transmitted and the receiver uses only the received semantic information to carry out the classification.

To design such a semantic communication system, the optimization problem is usually formulated to maximize the mutual information between the received symbols at the decoder and the semantic variable. However, as the direct optimization of the mutual information is intractable as the optimal decoder is not available, a lower bound is usually optimized instead. Furthermore, in cases, where the data to be reconstructed has high dimensionality, e.g. for distributed function computation with a large number of outputs, or when the full data shall be reconstructed at the same time as the reconstruction of the semantic variable, the optimization of the mutual information lower bound is computationally infeasible. One approach in this case is the assumption of a parameterized distribution for the decoder, which then can be optimized. Often, simply a Gaussian distribution is assumed. However, it is an open question whether a Gaussian is a sensible choice depending on the dataset.

[1] Beck E, Bockelmann C, Dekorsy A. Semantic Information Recovery in Wireless Networks. Sensors. 2023; 23(14):6347. https://doi.org/10.3390/s23146347

Possible objectives:

• Develop and implement a simulation model of a semantic encoder decoder structure using deep neural networks

• Investigate semantic communication for distributed function computation for non-linear functions.

• Perform numeric evaluations of the developed simulation model

Requirements:

• Information theory background knowledge

• Basic knowledge of machine learning

• Programming skills (python)

If you are interested in the topic for a master’s thesis, do not hesitate to contact me for more information: tillmann@ant.uni-bremen.de