Deep learning has achieved remarkable success in many machine learning tasks such as
image classification, speech recognition, and game playing. However, these breakthroughs …

Among the main features of biological intelligence are energy efficiency, capacity for
continual adaptation, and risk management via uncertainty quantification. Neuromorphic …

This work takes a critical look at the application of conventional machine learning methods
to wireless communication problems through the lens of reliability and robustness. Deep …

Two of the main principles underlying the life cycle of an artificial intelligence (AI) module in
communication networks are adaptation and monitoring. Adaptation refers to the need to …

In the design of wireless receivers, deep neural networks (DNNs) can be combined with
traditional model-based receiver algorithms to realize modular hybrid model-based/data …

Conventional frequentist federated learning (FL) schemes are known to yield overconfident
decisions. Bayesian FL addresses this issue by allowing agents to process and exchange …

Meta-learning, or learning to learn, offers a principled framework for few-shot learning. It
leverages data from multiple related learning tasks to infer an inductive bias that enables …

Accurate uncertainty quantification in graph neural networks (GNNs) is essential, especially
in high-stakes domains where GNNs are frequently employed. Conformal prediction (CP) …

Machine unlearning refers to mechanisms that can remove the influence of a subset of
training data upon request from a trained model without incurring the cost of re-training from …

According to Wheeler (2016: 2), machine learning is a “marriage of statistics and computer
science that began in artificial intelligence”. While statistics deals with the question of what …