Machine Learning Model
Machine learning models aim to create systems that can learn from data and make predictions or decisions without explicit programming. Current research emphasizes improving model accuracy, interpretability, and robustness, focusing on architectures like deep neural networks, decision tree ensembles, and transformer models, as well as exploring decentralized learning and techniques for mitigating biases and vulnerabilities. These advancements are crucial for diverse applications, ranging from optimizing resource management (e.g., smart irrigation) to improving healthcare diagnostics and enhancing the security and trustworthiness of AI systems.
Papers
Fill In The Gaps: Model Calibration and Generalization with Synthetic Data
Yang Ba, Michelle V. Mancenido, Rong Pan
Optimizing Parking Space Classification: Distilling Ensembles into Lightweight Classifiers
Paulo Luza Alves, André Hochuli, Luiz Eduardo de Oliveira, Paulo Lisboa de Almeida
An Effective Theory of Bias Amplification
Arjun Subramonian, Samuel J. Bell, Levent Sagun, Elvis Dohmatob
On the Robustness of Machine Learning Models in Predicting Thermodynamic Properties: a Case of Searching for New Quasicrystal Approximants
Fedor S. Avilov, Roman A. Eremin, Semen A. Budennyy, Innokentiy S. Humonen
Causal Inference Tools for a Better Evaluation of Machine Learning
Michaël Soumm
A Federated Learning Platform as a Service for Advancing Stroke Management in European Clinical Centers
Diogo Reis Santos, Albert Sund Aillet, Antonio Boiano, Usevalad Milasheuski, Lorenzo Giusti, Marco Di Gennaro, Sanaz Kianoush, Luca Barbieri, Monica Nicoli, Michele Carminati, Alessandro E. C. Redondi, Stefano Savazzi, Luigi Serio
Deep Unlearn: Benchmarking Machine Unlearning
Xavier F. Cadet, Anastasia Borovykh, Mohammad Malekzadeh, Sara Ahmadi-Abhari, Hamed Haddadi