相关论文: Low-Energy On-Device Personalization for MCUs
On-device training is essential for user personalisation and privacy. With the pervasiveness of IoT devices and microcontroller units (MCUs), this task becomes more challenging due to the constrained memory and compute resources, and the…
On-device learning enables edge devices to continually adapt the AI models to new data, which requires a small memory footprint to fit the tight memory constraint of edge devices. Existing work solves this problem by reducing the number of…
Recent advancements in machine learning (ML) have enabled its deployment on resource-constrained edge devices, fostering innovative applications such as intelligent environmental sensing. However, these devices, particularly…
Energy-efficient machine learning models that can run directly on edge devices are of great interest in IoT applications, as they can reduce network pressure and response latency, and improve privacy. An effective way to obtain…
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 smaller even than mobile phones. We propose MCUNet, a framework that jointly…
Machine learning (ML) is moving towards edge devices. However, ML models with high computational demands and energy consumption pose challenges for ML inference in resource-constrained environments, such as the deep sea. To address these…
The personalization of machine learning (ML) models to address data drift is a significant challenge in the context of Internet of Things (IoT) applications. Presently, most approaches focus on fine-tuning either the full base model or its…
Existing pruning methods are typically applied during training or compile time and often rely on structured sparsity. While compatible with low-power microcontrollers (MCUs), structured pruning underutilizes the opportunity for fine-grained…
Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devices, but existing training methods for these compact models…
Edge learning facilitates ubiquitous intelligence by enabling model training and adaptation directly on data-generating devices, thereby mitigating privacy risks and communication latency. However, the high computational and energy overhead…
Printed electronics have gained significant traction in recent years, presenting a viable path to integrating computing into everyday items, from disposable products to low-cost healthcare. However, the adoption of computing in these…
In the context of the Internet of Things (IoT), reliable and energy-efficient provision of IoT applications has become critical. Equipping IoT systems with tools that enable a flexible, well-performing, and automated way of monitoring and…
Contextual Artificial Intelligence (AI) based on emerging Transformer models is predicted to drive the next technology revolution in interactive wearable devices such as new-generation smart glasses. By coupling numerous sensors with small,…
The proliferation of smart and autonomous systems has motivated a shift toward executing intelligence directly on edge devices. This shift becomes particularly challenging for zero-energy devices (ZEDs), where severe constraints on memory,…
On-device training is an emerging approach in machine learning where models are trained on edge devices, aiming to enhance privacy protection and real-time performance. However, edge devices typically possess restricted computational power…
Achieving long battery lives or even self sustainability has been a long standing challenge for designing mobile devices. This paper presents a novel solution that seamlessly integrates two technologies, mobile cloud computing and microwave…
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 to transfer the data to the cloud, protecting the privacy.…
IoT devices based on microcontroller units (MCU) provide ultra-low power consumption and ubiquitous computation for near-sensor deep learning models (DNN). However, the memory of MCU is usually 2-3 orders of magnitude smaller than mobile…
Fast model updates for unseen tasks on intelligent edge devices are crucial but also challenging due to the limited computational power. In this paper,we propose MetaLDC, which meta-trains braininspired ultra-efficient low-dimensional…
Extreme edge devices or Internet-of-thing nodes require both ultra-low power always-on processing as well as the ability to do on-demand sampling and processing. Moreover, support for IoT applications like voice recognition, machine…