The unprecedented accuracy of convolutional neural networks (CNNs) acros...
On-device training is essential for user personalisation and privacy. Wi...
The ubiquity of camera-enabled devices has led to large amounts of unlab...
Combining Domain-adaptive Pre-training (DAPT) with Federated Learning (F...
Federated learning (FL) systems are susceptible to attacks from maliciou...
Most work in privacy-preserving federated learning (FL) has been focusin...
Conventional multiply-accumulate (MAC) operations have long dominated
co...
Human Activity Recognition (HAR) training data is often privacy-sensitiv...
The majority of work in privacy-preserving federated learning (FL) has b...
Federated Learning (FL) enables training ML models on edge clients witho...
The privacy-sensitive nature of decentralized datasets and the robustnes...
Aggregating pharmaceutical data in the drug-target interaction (DTI) dom...
In recent years, image and video delivery systems have begun integrating...
Recent image degradation estimation methods have enabled single-image
su...
Embedded and IoT devices, largely powered by microcontroller units (MCUs...
Deep Learning has proliferated dramatically across consumer devices in l...
Self-supervised learning (SSL) has proven vital in speech and audio-rela...
With deep neural networks (DNNs) emerging as the backbone in a multitude...
Attention-based neural networks have become pervasive in many AI tasks.
...
Federated Learning (FL) has emerged as a prospective solution that
facil...
As the use of AI-powered applications widens across multiple domains, so...
Federated Learning (FL) allows parties to learn a shared prediction mode...
The ubiquity of microphone-enabled devices has lead to large amounts of
...
We propose defensive tensorization, an adversarial defence technique tha...
Embedded and personal IoT devices are powered by microcontroller units
(...
With smartphones' omnipresence in people's pockets, Machine Learning (ML...
The annotation of domain experts is important for some medical applicati...
Deep learning-based blind super-resolution (SR) methods have recently
ac...
Differentiable neural architecture search (NAS) has attracted significan...
DNNs are becoming less and less over-parametrised due to recent advances...
Internet-enabled smartphones and ultra-wide displays are transforming a
...
Semantic segmentation arises as the backbone of many vision systems, spa...
Training Automatic Speech Recognition (ASR) models under federated learn...
Recently, there has been an explosive growth of mobile and embedded
appl...
Federated Learning (FL) allows edge devices to collaboratively learn a s...
Training and deploying graph neural networks (GNNs) remains difficult du...
Single computation engines have become a popular design choice for FPGA-...
Federated Learning (FL) has been gaining significant traction across
dif...
On-device machine learning is becoming a reality thanks to the availabil...
Neural Architecture Search (NAS) is quickly becoming the standard method...
Protective behavior exhibited by people with chronic pain (CP) during
ph...
IoT devices are powered by microcontroller units (MCUs) which are extrem...
The era of edge computing has arrived. Although the Internet is the back...
Despite impressive results, deep learning-based technologies also raise
...
Internet-enabled smartphones and ultra-wide displays are transforming a
...
This paper introduces a new dataset, Libri-Adapt, to support unsupervise...
Despite the soaring use of convolutional neural networks (CNNs) in mobil...
Graph neural networks (GNNs) have demonstrated strong performance on a w...
LPCNet is an efficient vocoder that combines linear prediction and deep
...
Convolutional neural networks (CNNs) have recently become the
state-of-t...