Abstract: Malicious insiders who possess system access and security expertise are notoriously difficult to detect and can inflict severe financial damage. While recent advances in deep learning have ...

Abstract: While traditional electrocardiogram (ECG) monitoring provides vital clinical information, its electrode-based setup restricts patient movement. To address this limitation, contactless ECG ...

In this project, we explore the use of autoencoders, a fundamental technique in deep learning, to reconstruct images from two distinct datasets: MNIST and CIFAR-10. The objective is to create an ...

Sparse autoencoders are central tools in analyzing how large language models function internally. Translating complex internal states into interpretable components allows researchers to break down ...

Dimensionality reduction is a method used in machine learning and data science to reduce the dimensions in a dataset. While linear methods are generally less effective at dimensionality reduction than ...