Last-level caches (LLCs) are large structures with significant power requirements. They can be quite inefficient. On average, a cache block in a 2MB LRU-managed LLC is dead 86% of ...
Samira Manabi Khan, Yingying Tian, Daniel A. Jimen...
The need for early detection of temporal events from sequential data arises in a wide spectrum of applications ranging from human-robot interaction to video security. While tempor...
We propose a family of kernels between images, defined as kernels between their respective segmentation graphs. The kernels are based on soft matching of subtree-patterns of the r...
This paper presents our experience in providing students with the best course material possible for the distance learning system at the University of Bucharest. We adapted each ye...
Mihaela Gheorghe, Michaela Logofatu, Daniel Horhoc...
Learning the underlying model from distributed data is often useful for many distributed systems. In this paper, we study the problem of learning a non-parametric model from distr...