The remarkable performance of deep Convolutional neural networks (CNNs) is generally
attributed to their deeper and wider architectures, which can come with significant …

Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs
with a few data. The main challenge is how to avoid overfitting since over-parameterized …

Various mobile and edge devices have significantly different processing capabilities, making
it challenging to develop a single universal architecture of a neural network to extract facial …

Differentiable architecture search (DAS) has become the prominent approach in the field of
neural architecture search (NAS) due to its time-efficient automation of neural network …

As model finetuning is central to the modern NLP, we set to maximize its efficiency.
Motivated by redundancy in training examples and the sheer sizes of pretrained models, we …

The convincing performances of deep neural networks (DNNs) can be degraded
tremendously under malicious samples, known as adversarial examples. Besides, with the …

Few-Shot Learning (FSL) refers to the problem of learning the underlying pattern in the data
just from a few training samples. However, when using transfer learning to solve few-shot …

The past decade has been witnessing remarkable advancements in computer vision and
deep learning algorithms, ushering in a transformative wave of large-scale edge …

The escalating complexity of state-of-the-art machine learning (ML) models is marked by
their expanding parameters and the substantial floating-point operations (FLOPs) required …