Deep learning (DL) algorithms have shown remarkable potential in automating various tasks
in medical imaging and radiologic reporting. However, models trained on low quantities of …

Machine learning is expected to fuel significant improvements in medical care. To ensure
that fundamental principles such as beneficence, respect for human autonomy, prevention of …

Abstract In many Reinforcement Learning (RL) tasks, the classical online interaction of the
learning agent with the environment is impractical, either because such interaction is …

Background Concept drift and covariate shift lead to a degradation of machine learning (ML)
models. The objective of our study was to characterize sudden data drift as caused by the …

Natural distribution shift causes a performance deterioration for the visual perception
computed by convolutional neural networks (CNNs). This can lead to safety–critical …

Internet of things (IoT) based smart city applications rely on constant data collection and
accurate data analytics, yet the fast-changing nature of such data often causes the …

Due to the limited computational capabilities, low memory and limited energy budget,
training deep neural networks on edge devices is very challenging. On the other hand …

We introduce the concept of history-restricted no-regret online learning algorithms. An online
learning algorithm $\mathcal {A} $ is $ M $-history-restricted if its output at time $ t $ can be …

Unstationary data can cause a change or drift in the machine learning model's context (ie
understanding of information) and/or concept (ie relationship between context and target) …

In research on applying Machine learning to Embedded systems in the field, little research
has been done in the evaluation of deployed devices. Often a system is trained with lots of …