We present Antler, which exploits the affinity between all pairs of tasks in a multitask
inference system to construct a compact graph representation of the task set and finds an …

While the global healthcare market of wearable devices has been growing significantly in
recent years and is predicted to reach $60 billion by 2028, many important healthcare …

Continual Learning (CL) allows applications such as user personalization and household
robots to learn on the fly and adapt to context. This is an important feature when context …

DTMM is a library designed for efficient deployment and execution of machine learning
models on weak IoT devices such as microcontroller units (MCUs). The motivation for …

With the increasing demand for Web of Things (WoT) and edge computing, the efficient
utilization of limited computing power on edge devices is becoming a crucial challenge …

Anomaly detection in the industrial context, identifying defective products and their
categorization, is a prevalent task. It is aimed to acknowledge if training and testing …

The real implementation of a recurrent neural network (RNN) in a low complexity IoT device
is evaluated in order to predict the time series of power consumption in tertiary buildings …

The ubiquity of executing machine learning tasks on embedded systems with constrained
resources has made efficient execution of neural networks on these systems under the CPU …

Maintaining a sufficient battery life-time is crucial for an everyday wearable instrumented
frame. Therefore, the use of a low-power integrated circuit, such as a microcontroller unit …

2. Background. This chapter describes the relevant research in more details in the areas of
on-device ML and CL to discuss the necessity, novelty, and contributions of this thesis. 3 …