8 papers
Competition, stability, and functionality in excitatory-inhibitory neural circuits
Simone Betteti, William Retnaraj, Alexander Davydov +2
Energy-based models have become a central paradigm for understanding computation and stability in both theoretical neuroscience and machine learning. However, the energetic framewo…
Timescale Limits of Linear-Threshold Networks
William Retnaraj, Simone Betteti, Alexander Davydov +2
Linear-threshold networks (LTNs) capture the mesoscale behavior of interacting populations of neurons and are of particular interest to control theorists due to their dynamical ric…
Hybrid Energy-Based Models for Physical AI: Provably Stable Identification of Port-Hamiltonian Dynamics
Simone Betteti, Luca Laurenti
Energy-based models (EBMs) implement inference as gradient descent on a learned Lyapunov function, yielding interpretable, structure-preserving alternatives to black-box neural ODE…
A Dynamical Theory of Sequential Retrieval in Input-Driven Hopfield Networks
Simone Betteti, Giacomo Baggio, Sandro Zampieri
Reasoning is the ability to integrate internal states and external inputs in a meaningful and semantically consistent flow. Contemporary machine learning (ML) systems increasingly…
Incremental Input-to-State Stability and Equilibrium Tracking for Stochastic Contracting Dynamics
Yu Kawano, Simone Betteti, Alexander Davydov +1
In this paper, we study the contractivity of nonlinear stochastic differential equations (SDEs) driven by deterministic inputs and Brownian motions. Given a weighted -norm…
Contraction and concentration of measures with applications to theoretical neuroscience
Simone Betteti, Francesco Bullo
We investigate the asymptotic behavior of probability measures associated with stochastic dynamical systems featuring either globally contracting or -contracting drift terms…