6 papers
An Energy-Based Mechanism for Compositional Behavior
Francesca Rossi, Veronica Centorrino, Francesco Bullo +1
Flexible intelligence relies on the ability to reuse previously acquired behaviors and combine them differently as circumstances change. In biological and artificial systems, this…
Similarity Matching Networks: Hebbian Learning and Convergence Over Multiple Time Scales
Veronica Centorrino, Francesco Bullo, Giovanni Russo
A recent breakthrough in biologically-plausible normative frameworks for dimensionality reduction is based upon the similarity matching cost function and the low-rank matrix approx…
Proximal Gradient Dynamics and Feedback Control for Equality-Constrained Composite Optimization
Veronica Centorrino, Francesca Rossi, Francesco Bullo +1
This paper studies equality-constrained composite minimization problems. This class of problems, capturing regularization terms and inequality constraints, naturally arises in a wi…
Free-Gate: Planning, Control And Policy Composition via Free Energy Gating
Francesca Rossi, Émiland Garrabé, Giovanni Russo
We consider the problem of optimally composing a set of primitives to tackle planning and control tasks. To address this problem, we introduce a free energy computational model for…
On Weakly Contracting Dynamics for Convex Optimization
Veronica Centorrino, Alexander Davydov, Anand Gokhale +2
We analyze the convergence behavior of \emph{globally weakly} and \emph{locally strongly contracting} dynamics. Such dynamics naturally arise in the context of convex optimization…
Positive Competitive Networks for Sparse Reconstruction
Veronica Centorrino, Anand Gokhale, Alexander Davydov +2
We propose and analyze a continuous-time firing-rate neural network, the positive firing-rate competitive network (\pfcn), to tackle sparse reconstruction problems with non-negativ…