Meta-learning aims to leverage prior knowledge from related tasks to enable a base learner
to quickly adapt to new tasks with limited labeled samples. However, traditional meta …

Learning models that can generalize to previously unseen domains to which we have no
access is a fundamental yet challenging problem in machine learning. In this paper, we …

Over the years, most research towards defenses against adversarial attacks on machine
learning models has been in the image recognition domain. The ML-based malware …

Meta-learning, a rapidly advancing area in computational intelligence, leverages prior
knowledge from related tasks to facilitate the swift adaptation to new tasks with limited data …

Abstract Domain generalization has recently generated increasing attention in machine
learning in that it tackles the challenging out-of-distribution problem. The huge domain shift …

Abstract Machine learning (ML) has facilitated progress in several disciplines as a result of
greater resources, data volumes, and algorithmic developments. Particularly in …

ResNet34 is one of the important models for image classification, and research has found
that ResNet34 has problems such as information loss, low accuracy, and training difficulties …

Random feature methods and neural network models are two popular nonparametric
modeling methods, which are regarded as representatives of shallow learning and Neural …