Federated learning (FL) is a distributed machine learning strategy that generates a global
model by learning from multiple decentralized edge clients. FL enables on-device training …

The rapid growth in miniaturization of low-power embedded devices and advancement in
the optimization of machine learning (ML) algorithms have opened up a new prospect of the …

On-device training enables the model to adapt to new data collected from the sensors by
fine-tuning a pre-trained model. Users can benefit from customized AI models without having …

This chapter provides approaches to the problem of quantizing the numerical values in deep
Neural Network computations, covering the advantages/disadvantages of current methods …

Abstract Machine learning on tiny IoT devices based on microcontroller units (MCU) is
appealing but challenging: the memory of microcontrollers is 2-3 orders of magnitude …

Transformer based models, like BERT and RoBERTa, have achieved state-of-the-art results
in many Natural Language Processing tasks. However, their memory footprint, inference …

Tiny deep learning on microcontroller units (MCUs) is challenging due to the limited memory
size. We find that the memory bottleneck is due to the imbalanced memory distribution in …

The advancements in machine learning (ML) opened a new opportunity to bring intelligence
to the low-end Internet-of-Things (IoT) nodes, such as microcontrollers. Conventional ML …

Successful integration of deep neural networks (DNNs) or deep learning (DL) has resulted
in breakthroughs in many areas. However, deploying these highly accurate models for data …

The rapid emergence of low-power embedded devices and modern machine learning (ML)
algorithms has created a new Internet of Things (IoT) era where lightweight ML frameworks …