New Machine
Research on "new machines" broadly encompasses the development and application of machine learning across diverse fields, aiming to improve efficiency, accuracy, and decision-making. Current efforts focus on refining model architectures like convolutional neural networks, gradient boosting machines, and transformers for tasks ranging from image and signal processing to complex prediction and control problems. This research is significant because it drives advancements in various sectors, including healthcare, energy, manufacturing, and transportation, by enabling automated processes, improved diagnostics, and more efficient resource allocation.
Papers
Self-learning locally-optimal hypertuning using maximum entropy, and comparison of machine learning approaches for estimating fatigue life in composite materials
Ismael Ben-Yelun, Miguel Diaz-Lago, Luis Saucedo-Mora, Miguel Angel Sanz, Ricardo Callado, Francisco Javier Montans
Performance of different machine learning methods on activity recognition and pose estimation datasets
Love Trivedi, Raviit Vij
A machine learning based algorithm selection method to solve the minimum cost flow problem
Philipp Herrmann, Anna Meyer, Stefan Ruzika, Luca E. Schäfer, Fabian von der Warth
Machine Learning-Powered Course Allocation
Ermis Soumalias, Behnoosh Zamanlooy, Jakob Weissteiner, Sven Seuken
Privacy-Preserving Feature Coding for Machines
Bardia Azizian, Ivan V. Bajić