A
Andrea Bartolini
Researcher at University of Bologna
Publications - 176
Citations - 2482
Andrea Bartolini is an academic researcher from University of Bologna. The author has contributed to research in topics: Supercomputer & Computer science. The author has an hindex of 25, co-authored 150 publications receiving 1980 citations. Previous affiliations of Andrea Bartolini include École Polytechnique Fédérale de Lausanne & Marche Polytechnic University.
Papers
More filters
Journal ArticleDOI
Anomaly Detection Using Autoencoders in High Performance Computing Systems
TL;DR: A novel approach for anomaly detection in HighPerformance Computing systems based on a Machine (Deep) Learning technique, namely a type of neural network called autoencoder, capable of detecting anomalies that have never been seen before with a very good accuracy.
Journal ArticleDOI
Thermal and Energy Management of High-Performance Multicores: Distributed and Self-Calibrating Model-Predictive Controller
TL;DR: A scalable, fully distributed, energy-aware thermal management solution for single-chip multicore platforms is presented and model uncertainty is addressed by supporting learning of the thermal model with a novel distributed self-calibration approach that matches well the controller architecture.
Journal ArticleDOI
Empirical decision model learning
TL;DR: This paper proposes a methodology called Empirical Model Learning (EML) that relies on Machine Learning for obtaining components of a prescriptive model, using data either extracted from a predictive model or harvested from a real system, and uses two learning methods, namely Artificial Neural Networks and Decision Trees.
Proceedings ArticleDOI
A distributed and self-calibrating model-predictive controller for energy and thermal management of high-performance multicores
TL;DR: A scalable, fully-distributed, energy-aware thermal management solution that addresses model uncertainty by supporting learning of the thermal model with a novel distributed self-calibration approach that matches well the controller architecture.
Journal ArticleDOI
A semisupervised autoencoder-based approach for anomaly detection in high performance computing systems
TL;DR: A novel semi-supervised approach for anomaly detection in supercomputers is proposed, based on a type of neural network called autoencoder, which outperforms the best current techniques for semi- supervised anomaly detection, with an increase in accuracy detection of around 12%.