Eleni Vasilaki

An empirical comparison between stochastic and deterministic centroid initialisation for K-means variations

2021 · Machine Learning

Abstract K-Means is one of the most used algorithms for data clustering and the usual clustering method for benchmarking. Despite its wide application it is well-known that it suffers from a series of disadvantages; it …

A perspective on physical reservoir computing with nanomagnetic devices

2022 · arXiv (Cornell University)

Neural networks have revolutionized the area of artificial intelligence and introduced transformative applications to almost every scientific field and industry. However, this success comes at a great price; the energy requirements for training advanced models …