Chiara Marullo

Dr. Chiara Marullo

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 December 2020 in Entropy
Verified
Journal Article
Open access
PDF file
CMChiara Marullo
Chiara Marullo
EAElena Agliari
Elena Agliari
The Hopfield model and the Boltzmann machine are among the most popular examples of neural networks. The latter, widely used for classification and feature detection, is able to efficiently learn a generative model from observed data and constitutes the benchmark for statistical learning. The former, designed to mimic the retrieval phase of an artificial associative memory lays in between two paradigmatic statistical mechanics models, namely the Curie-Weiss and the Sherrington-Kirkpatrick, which are recovered as the limiting cases of, respectively, one and many stored memories. Interestingly, the Boltzmann machine and the Hopfield network, if considered to be two cognitive processes (learning and information retrieval), are nothing more than two sides of the same coin. In fact, it is possible to exactly map the one into the other. We will inspect such an equivalence retracing the most representative steps of the research in this field.

18 April 2023 in Neural Computation
Verified
Journal Article
Closed access
PDF file
EAElena Agliari
Elena Agliari
MAMiriam Aquaro
Miriam Aquaro
ABAdriano Barra
Adriano Barra
AFAlberto Fachechi
Alberto Fachechi
CMChiara Marullo
Chiara Marullo
Hebb's learning traces its origin in Pavlov's classical conditioning; however, while the former has been extensively modeled in the past decades (e.g., by the Hopfield model and countless variations on theme), as for the latter, modeling has remained largely unaddressed so far. Furthermore, a mathematical bridge connecting these two pillars is totally lacking. The main difficulty toward this goal lies in the intrinsically different scales of the information involved: Pavlov's theory is about correlations between concepts that are (dynamically) stored in the synaptic matrix as exemplified by the celebrated experiment starring a dog and a ringing bell; conversely, Hebb's theory is about correlations between pairs of neurons as summarized by the famous statement that neurons that fire together wire together. In this letter, we rely on stochastic process theory to prove that as long as we keep neurons' and synapses' timescales largely split, Pavlov's mechanism spontaneously takes place and ultimately gives rise to synaptic weights that recover the Hebbian kernel.

1 October 2022 in Journal of Mathematical Physics
Verified
Journal Article
Closed access
PDF file
EAElena Agliari
Elena Agliari
AFAlberto Fachechi
Alberto Fachechi
CMChiara Marullo
Chiara Marullo
Dense associative memories (DAMs) are widely used models in artificial intelligence for pattern recognition tasks; computationally, they have been proven to be robust against adversarial inputs and, theoretically, leveraging their analogy with spin-glass systems, they are usually treated by means of statistical-mechanics tools. Here, we develop analytical methods, based on nonlinear partial differential equations, to investigate their functioning. In particular, we prove differential identities involving DAM’s partition function and macroscopic observables useful for a qualitative and quantitative analysis of the system. These results allow for a deeper comprehension of the mechanisms underlying DAMs and provide interdisciplinary tools for their study.

1 December 2020 in Journal of Mathematical Physics
Verified
Journal Article
Closed access
PDF file
EAElena Agliari
Elena Agliari
AFAlberto Fachechi
Alberto Fachechi
CMChiara Marullo
Chiara Marullo
In this work, we introduce and investigate the properties of the “relativistic” Hopfield model endowed with temporally correlated patterns. First, we review the “relativistic” Hopfield model and we briefly describe the experimental evidence underlying correlation among patterns. Then, we face the study of the resulting model exploiting statistical-mechanics tools in a low-load regime. More precisely, we prove the existence of the thermodynamic limit of the related free energy and we derive the self-consistence equations for its order parameters. These equations are solved numerically to get a phase diagram describing the performance of the system as an associative memory as a function of its intrinsic parameters (i.e., the degree of noise and of correlation among patterns). We find that beyond the standard retrieval and ergodic phases, the relativistic system exhibits correlated and symmetric regions, which are genuine effects of temporal correlation, whose width is, respectively, reduced and increased with respect to the classical case.

22 January 2023 in Entropy
Verified
Journal Article
Open access
PDF file
FCFabio Ciolli
Fabio Ciolli
FFFrancesco Fidaleo
Francesco Fidaleo
CMChiara Marullo
Chiara Marullo
The aim of the present paper is to provide a preliminary investigation of the thermodynamics of particles obeying monotone statistics. To render the potential physical applications realistic, we propose a modified scheme called block-monotone, based on a partial order arising from the natural one on the spectrum of a positive Hamiltonian with compact resolvent. The block-monotone scheme is never comparable with the weak monotone one and is reduced to the usual monotone scheme whenever all the eigenvalues of the involved Hamiltonian are non-degenerate. Through a detailed analysis of a model based on the quantum harmonic oscillator, we can see that: (a) the computation of the grand-partition function does not require the Gibbs correction factor n! (connected with the indistinguishability of particles) in the various terms of its expansion with respect to the activity; and (b) the decimation of terms contributing to the grand-partition function leads to a kind of “exclusion principle” analogous to the Pauli exclusion principle enjoined by Fermi particles, which is more relevant in the high-density regime and becomes negligible in the low-density regime, as expected.

31 January 2025 in Reviews in Mathematical Physics
Verified
Journal Article
Closed access
CMChiara Marullo
Chiara Marullo
GBGiuseppe Buonaiuto
Giuseppe Buonaiuto
Daniele CianiDaniele Ciani
Daniele Ciani
Francesco GargiuloFrancesco Gargiulo
Francesco Gargiulo
Massimo EspositoMassimo Esposito
Massimo Esposito