The New Special Issue "Information-Theoretic Approaches for Machine Learning and AI" is Open for Submission!

Guest Editors: Prof. Songze Li and Dr. Linqi Song

Submit to the Special Issue: https://www.mdpi.com/journal/entropy/special_issues/LN920MA8EK

Submission deadline: 25 April 2025

Special Issue Information: With the rapid development of artificial intelligence (AI) technology, especially large language models, the ways in which information is acquired, processed, and transmitted are undergoing revolutionary changes. In this context, Shannon entropy and information theory, as fundamental theories for understanding and measuring information, play a crucial role.

As the complexity of deep learning models continues to increase, their internal mechanisms often become a “black box”, posing challenges to the credibility and application of these models. By introducing methods from information theory, we can explore how to quantify the uncertainty and information flow within models, thereby revealing their decision-making processes. This not only aids in understanding the internal workings of the models but also provides effective guidance for model optimization and downstream tasks, such as multimodal compression and knowledge editing. Simultaneously, quantum entropy and quantum information theory offer entirely new perspectives and tools, which are expected to propel the forefront of AI in computational capabilities, algorithm design, and secure communication. Coding theory also plays a critical role in machine learning, by improving the efficiency, privacy, and security of data processing through information encoding and error correction.

The aim of this Special Issue is to attract research investigations, from an information–theoretic perspective, addressing current challenges faced by theory and applications of machine learning. Prospective authors are invited to submit original research contributions on leveraging information theory and quantum information theory, in solving problems on (but not limited to) the following topics:

Model interpretability;

Reinforcement learning;

Data compression and semantic communication;

Federated learning;

Large language models;

Optimization;

Sustainable AI;

Security and privacy;

Unbiasedness and fairness in AI.