Francesco Bullo
3 papers · Latest:
Timescale Limits of Linear-Threshold Networks
This paper explores global stability in linear-threshold networks by analyzing fast and slow limits, revealing key stability mechanisms.
2604.16710
A Nonlinear Separation Principle: Applications to Neural Networks, Control and Learning
This paper introduces a nonlinear separation principle for recurrent neural networks, enabling stable control design and efficient implicit deep learning.
2604.15238
Machine LearningEnergy-Based Dynamical Models for Neurocomputation, Learning, and Optimization
This tutorial explores energy-based dynamical models, bridging neuroscience, control theory, and machine learning for scalable, robust, and energy-efficient computation.
2604.05042
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.