arXiv subjects

Adriano Barra

Publications and source records attributed to Adriano Barra.

At least 19 recordsLinked to original sources

arXiv2026

Exponential Capacity in Multilayer Hetero-Associative Neural Networks

Exponential Hopfield networks store a number of patterns that grows exponentially with the number of neurons, and in their classical formulation they are auto-associative: they complete a corrupted copy of a memory into the memory itself. Many of the tasks one wants such a network to perform are instead hetero-associative, mapping a cue to a different target. We introduce and analyse an exponential neural network of $L$ layers of $N$ binary neurons, each layer carrying its own dataset, whose energy is an exponential of the product of the per-layer Mattis overlaps, so that it is minimised precisely when every layer retrieves the pattern of the same index; the stored association must be a surjective function of the cue, and we show why nothing else can be stored at all. A cavity/signal-to-noise analysis, made exact at leading order by a large-deviation evaluation of the noise, shows that the aligned hetero-associative state is a fixed point of the zero-temperature dynamics up to a number of stored patterns $P_c\sim e^{N\rho_L}$, exponential in the layer size, with an explicit rate $\rho_L$ that grows like $L\log 2$; enlarging the basins of attraction lowers the rate but never destroys its exponential character. Comparing the theory with structured data we find that the exponential capacity and the predicted basins survive correlated, many-to-one patterns: the network is a near-perfect content-addressable memory. The same closed forms describe, without refitting, a synthetic manifold, real T-cell-receptor/epitope triples and natural-language intent data, so the mechanism is domain-universal. Generalisation to unseen cues, though significantly above chance, stays below memorisation, and it is the geometry of the encoding, rather than the data domain, that sets how far above chance it reaches. In this family, exponential storage and strong generalisation are distinct capabilities.

cond-mat.dis-nn↗

arXiv2026

Do Hopfield Networks Dream of Stored Patterns? A Statistical-Mechanical Theory of Dreaming in Multidirectional Associative Memories

We introduce the Dreaming $L$-directional Associative Memory (DLAM), a multi-layer Hebbian architecture in which off-line dreaming and supervised heteroassociative coupling coexist within a single energy function, placing our approach within the framework of energy-based models (EBMs). The replica-symmetric free energy, derived via the Guerra interpolation scheme, yields self-consistency equations governing the order parameters across the control-parameter space. The effective local field decomposes into signal, intra-layer dreaming noise, and inter-layer noise. Dreaming improves retrieval by differentially attenuating high-eigenvalue interference modes of the empirical correlation matrix, suppressing inter-pattern crosstalk while preserving the signal. Dreaming and inter-layer coupling prove synergistic, opening retrieval regions unreachable by either mechanism alone, as confirmed by Monte Carlo simulations for $L=3$. Their interplay is most pronounced on pattern disentanglement: given a mixture state as input, the network splits the constituent patterns one-per-layer, recovering each modality-specific pattern from a common cue that simultaneously blends noisy evidence from all sensory channels. Phase diagrams are planar projections of the hyperspace $(\alpha,\beta,\rho,t)$-where $\alpha$ is the storage load, $\beta$ the fast-noise inverse temperature, $\rho$ the dataset entropy, and $t$ the sleeping time. In the $(\rho,t)$-plane, the diagrams reveal a data-computation trade-off: off-line consolidation substitutes for additional training data, extending to heteroassociative architectures a phenomenon previously established for autoassociative networks. Enriching the standard Hopfield model with heteroassociativity and dreaming gives rise to EBMs capable of complex tasks beyond classical pattern recognition, contributing to a modern theory of neural information processing.

cond-mat.dis-nn↗

arXiv2026

Partial annealing and pattern decorrelation in associative neural networks

Using the Hopfield model as a benchmark case, the present work focuses on the investigation of partially annealed associative neural networks, wherein neural dynamics is coupled to slowly evolving patterns within the two-temperature-two-timescale framework. This setting inherently introduces a real parameter n, reminiscent of the number of replicas in the celebrated replica trick, that tunes the separation of timescales and the effective interaction between fast (i.e. the neurons) and slow (i.e. the synapses) degrees of freedom. By adapting Guerra's interpolation to the case, we derive the free energy without relying on analytical continuation. The obtained results demonstrate that negative values of n induce a progressive decorrelation of the stored patterns, thereby effectively reducing interference, promoting orthogonal configurations and ultimately conferring to the network the maximal storage alphac=1. Numerical simulations based on a mean field Monte Carlo dynamics have been employed to confirm this scenario and prove that partial annealing restores retrieval in challenging regimes, such as in the presence of biased patterns, outperforming standard decorrelation methods. These findings underscore the notion of partial annealing as an adaptive mechanism for enhancing memory organisation and retrieval in complex systems.

cond-mat.dis-nn↗

arXiv2026

Serial vs parallel recall in the Blume-Every-Griffiths neural networks

Fully connected Blume-Emery-Griffiths neural networks performing pattern recognition and associative memory have been heuristically studied in the past (mainly via the replica trick and under the replica symmetric assumption) as generalization of the standard Hopfield reference. In these notes, at first, by relying upon Guerra interpolation, we re-obtain the existing picture rigorously. Next we show that, due to dilution in the patterns, these networks are able to switch from serial recall (where one pattern is retrieved per time) to parallel recall (where several patterns are retrieved at once) and the larger the dilution, the stronger this emerging multi-tasking capability. In particular, we inspect the regimes of mild dilution (where solely a low storage of pattern can be enabled) and extreme dilution (where a medium storage of patterns can be sustained) separately as they give rise to different outcomes: the former displays hierarchical recall (distributing the amplitudes of the retrieved signals with different amplitudes), the latter -- instead -- performs a equal-strength recall (where a O(1) fraction of all the patterns is simultaneously retrieved with the same amplitude per pattern). Finally, in order to implement graded responses in the neurons, variations on theme obtained by enlarging the possible values of neural activity these neurons may sustain are also discussed generalizing the Ghatak-Sherrington model for inverse freezing in Hebbian terms.

cond-mat.dis-nn↗

arXiv2025

On the supra-linear storage in dense networks of grid and place cells

Place-cell networks, typically forced to pairwise synaptic interactions, are widely studied as models of cognitive maps: such models, however, share a severely limited storage capacity, scaling linearly with network size and with a very small critical storage. This limitation is a challenge for navigation in 3-dimensional space because, oversimplifying, if encoding motion along a one-dimensional trajectory embedded in 2-dimensions requires $O(K)$ patterns (interpreted as bins), extending this to a 2-dimensional manifold embedded in a 3-dimensional space -- yet preserving the same resolution -- requires roughly $O(K^2)$ patterns, namely a supra-linear amount of patterns. In these regards, dense Hebbian architectures, where higher-order neural assemblies mediate memory retrieval, display much larger capacities and are increasingly recognized as biologically plausible, but have never linked to place cells so far. Here we propose a minimal two-layer model, with place cells building a layer and leaving the other layer populated by neural units that account for the internal representations (so to qualitatively resemble grid cells in the MEC of mammals): crucially, by assuming that each place cell interacts with pairs of grid cells, we show how such a model is formally equivalent to a dense Battaglia-Treves-like Hebbian network of grid cells only endowed with four-body interactions. By studying its emergent computational properties by means of statistical mechanics of disordered systems, we prove -- analytically -- that such effective higher-order assemblies (constructed under the guise of biological plausibility) can support supra-linear storage of continuous attractors; furthermore, we prove -- numerically -- that the present neural network is capable of recognition and navigation on general surfaces embedded in a 3-dimensional space.

cond-mat.dis-nn↗

arXiv2025

Yet another exponential Hopfield model

We propose and analyze a new variation of the so-called {\em exponential Hopfield model}, a recently introduced family of associative neural networks with unprecedented storage capacity. Our construction is based on a cost function defined through exponentials of standard quadratic loss functions, which naturally favors configurations corresponding to perfect recall. Despite not being a mean-field system, the model admits a tractable mathematical analysis of its dynamics and retrieval properties that agree with those for the original exponential model introduced by Ramsauer and coworkers. By means of a signal-to-noise approach, we demonstrate that stored patterns remain stable fixed points of the zero-temperature dynamics up to an exponentially large number of patterns in the system size. We further quantify the basins of attraction of the retrieved memories, showing that while enlarging their radius reduces the overall load, the storage capacity nonetheless retains its exponential scaling. An independent derivation within the perfect recall regime confirms these results and provides an estimate of the relevant prefactors. Our findings thus complement and extend previous studies on exponential Hopfield networks, establishing that even under robustness constraints these models preserve their exceptional storage capabilities. Beyond their theoretical interest, such networks point towards principled mechanisms for massively scalable associative memory, with potential implications for both neuroscience-inspired computation and high-capacity machine learning architectures.

cond-mat.dis-nn↗

arXiv2025

Supervised and Unsupervised protocols for hetero-associative neural networks

This paper introduces a learning framework for Three-Directional Associative Memory (TAM) models, extending the classical Hebbian paradigm to both supervised and unsupervised protocols within an hetero-associative setting. These neural networks consist of three interconnected layers of binary neurons interacting via generalized Hebbian synaptic couplings that allow learning, storage and retrieval of structured triplets of patterns. By relying upon glassy statistical mechanical techniques (mainly replica theory and Guerra interpolation), we analyze the emergent computational properties of these networks, at work with random (Rademacher) datasets and at the replica-symmetric level of description: we obtain a set of self-consistency equations for the order parameters that quantify the critical dataset sizes (i.e. their thresholds for learning) and describe the retrieval performance of these networks, highlighting the differences between supervised and unsupervised protocols. Numerical simulations validate our theoretical findings and demonstrate the robustness of the captured picture about TAMs also at work with structured datasets. In particular, this study provides insights into the cooperative interplay of layers, beyond that of the neurons within the layers, with potential implications for optimal design of artificial neural network architectures.

cond-mat.dis-nn↗

arXiv2025

Guerra interpolation for inverse freezing

In these short notes, we adapt and systematically apply Guerra's interpolation techniques on a class of disordered mean-field spin glasses equipped with crystal fields and multi-value spin variables. These models undergo the phenomenon of inverse melting or inverse freezing. In particular, we focus on the Ghatak-Sherrington model, its extension provided by Katayama and Horiguchi, and the disordered Blume-Emery-Griffiths-Capel model in the mean-field limit, deepened by Crisanti and Leuzzi and by Schupper and Shnerb. Once shown how all these models can be retrieved as particular limits of a unique broader Hamiltonian, we study their free energies. We provide explicit expressions of their annealed and quenched expectations, inspecting the cases of replica symmetry and (first-step) broken replica symmetry. We recover several results previously obtained via heuristic approaches (mainly the replica trick) to prove full agreement with the existing literature. As a sideline, we also inspect the onset of replica symmetry breaking by providing analytically the expression of the de Almeida-Thouless instability line for a replica symmetric description: in this general setting, the latter is new also from a physical viewpoint.

cond-mat.dis-nn↗

arXiv2025

Beyond Disorder: Unveiling Cooperativeness in Multidirectional Associative Memories

By leveraging tools from the statistical mechanics of complex systems, in these short notes we extend the architecture of a neural network for hetero-associative memory (called three-directional associative memories, TAM) to explore supervised and unsupervised learning protocols. In particular, by providing entropic-heterogeneous datasets to its various layers, we predict and quantify a new emergent phenomenon -- that we term {\em layer's cooperativeness} -- where the interplay of dataset entropies across network's layers enhances their retrieval capabilities Beyond those they would have without reciprocal influence. Naively we would expect layers trained with less informative datasets to develop smaller retrieval regions compared to those pertaining to layers that experienced more information: this does not happen and all the retrieval regions settle to the same amplitude, allowing for optimal retrieval performance globally. This cooperative dynamics marks a significant advancement in understanding emergent computational capabilities within disordered systems.

cond-mat.dis-nn↗

arXiv2025

Networks of neural networks: more is different

The common thread behind the recent Nobel Prize in Physics to John Hopfield and those conferred to Giorgio Parisi in 2021 and Philip Anderson in 1977 is disorder. Quoting Philip Anderson: "more is different". This principle has been extensively demonstrated in magnetic systems and spin glasses, and, in this work, we test its validity on Hopfield neural networks to show how an assembly of these models displays emergent capabilities that are not present at a single network level. Such an assembly is designed as a layered associative Hebbian network that, beyond accomplishing standard pattern recognition, spontaneously performs also pattern disentanglement. Namely, when inputted with a composite signal -- e.g., a musical chord -- it can return the single constituting elements -- e.g., the notes making up the chord. Here, restricting to notes coded as Rademacher vectors and chords that are their mixtures (i.e., spurious states), we use tools borrowed from statistical mechanics of disordered systems to investigate this task, obtaining the conditions over the model control-parameters such that pattern disentanglement is successfully executed.

cond-mat.dis-nn↗

arXiv2024

The thermodynamic limit in mean field neural networks

In the last five decades, mean-field neural-networks have played a crucial role in modelling associative memories and, in particular, the Hopfield model has been extensively studied using tools borrowed from the statistical mechanics of spin glasses. However, achieving mathematical control of the infinite-volume limit of the model's free-energy has remained elusive, as the standard treatments developed for spin-glasses have proven unfeasible. Here we address this long-standing problem by proving that a measure-concentration assumption for the order parameters of the theory is sufficient for the existence of the asymptotic limit of the model's free energy. The proof leverages the equivalence between the free energy of the Hopfield model and a linear combination of the free energies of a hard and a soft spin-glass, whose thermodynamic limits are rigorously known. Our work focuses on the replica-symmetry level of description (for which we recover the explicit expression of the free-energy found in the eighties via heuristic methods), yet, our scheme is expected to work also under (at least) the first step of replica symmetry breaking.

cond-mat.dis-nn↗

arXiv2024

Generalized hetero-associative neural networks

Auto-associative neural networks (e.g., the Hopfield model implementing the standard Hebbian prescription) serve as a foundational framework for pattern recognition and associative memory in statistical mechanics. However, their hetero-associative counterparts, though less explored, exhibit even richer computational capabilities. In this work, we examine a straightforward extension of Kosko's Bidirectional Associative Memory (BAM), introducing a Three-directional Associative Memory (TAM), that is a tripartite neural network equipped with generalized Hebbian weights. Through both analytical approaches (using replica-symmetric statistical mechanics) and computational methods (via Monte Carlo simulations), we derive phase diagrams within the space of control parameters, revealing a region where the network can successfully perform pattern recognition as well as other tasks tasks. In particular, it can achieve pattern disentanglement, namely, when presented with a mixture of patterns, the network can recover the original patterns. Furthermore, the system is capable of retrieving Markovian sequences of patterns and performing generalized frequency modulation.

cond-mat.dis-nn↗

arXiv2024

Guerra interpolation for place cells

Pyramidal cells that emit spikes when the animal is at specific locations of the environment are known as "place cells": these neurons are thought to provide an internal representation of space via "cognitive maps". Here, we consider the Battaglia-Treves neural network model for cognitive map storage and reconstruction, instantiated with McCulloch & Pitts binary neurons. To quantify the information processing capabilities of these networks, we exploit spin-glass techniques based on Guerra's interpolation: in the low-storage regime (i.e., when the number of stored maps scales sub-linearly with the network size and the order parameters self-average around their means) we obtain an exact phase diagram in the noise vs inhibition strength plane (in agreement with previous findings) by adapting the Hamilton-Jacobi PDE-approach. Conversely, in the high-storage regime, we find that -- for mild inhibition and not too high noise -- memorization and retrieval of an extensive number of spatial maps is indeed possible, since the maximal storage capacity is shown to be strictly positive. These results, holding under the replica-symmetry assumption, are obtained by adapting the standard interpolation based on stochastic stability and are further corroborated by Monte Carlo simulations (and replica-trick outcomes for the sake of completeness). Finally, by relying upon an interpretation in terms of hidden units, in the last part of the work, we adapt the Battaglia-Treves model to cope with more general frameworks, such as bats flying in long tunnels.

cond-mat.dis-nn↗

arXiv2024

Hebbian Learning from First Principles

Recently, the original storage prescription for the Hopfield model of neural networks -- as well as for its dense generalizations -- has been turned into a genuine Hebbian learning rule by postulating the expression of its Hamiltonian for both the supervised and unsupervised protocols. In these notes, first, we obtain these explicit expressions by relying upon maximum entropy extremization \`a la Jaynes. Beyond providing a formal derivation of these recipes for Hebbian learning, this construction also highlights how Lagrangian constraints within entropy extremization force network's outcomes on neural correlations: these try to mimic the empirical counterparts hidden in the datasets provided to the network for its training and, the denser the network, the longer the correlations that it is able to capture. Next, we prove that, in the big data limit, whatever the presence of a teacher (or its lacking), not only these Hebbian learning rules converge to the original storage prescription of the Hopfield model but also their related free energies (and, thus, the statistical mechanical picture provided by Amit, Gutfreund and Sompolinsky is fully recovered). As a sideline, we show mathematical equivalence among standard Cost functions (Hamiltonian), preferred in Statistical Mechanical jargon, and quadratic Loss Functions, preferred in Machine Learning terminology. Remarks on the exponential Hopfield model (as the limit of dense networks with diverging density) and semi-supervised protocols are also provided.

cond-mat.dis-nn↗

arXiv2023

Unsupervised and Supervised learning by Dense Associative Memory under replica symmetry breaking

Statistical mechanics of spin glasses is one of the main strands toward a comprehension of information processing by neural networks and learning machines. Tackling this approach, at the fairly standard replica symmetric level of description, recently Hebbian attractor networks with multi-node interactions (often called Dense Associative Memories) have been shown to outperform their classical pairwise counterparts in a number of tasks, from their robustness against adversarial attacks and their capability to work with prohibitively weak signals to their supra-linear storage capacities. Focusing on mathematical techniques more than computational aspects, in this paper we relax the replica symmetric assumption and we derive the one-step broken-replica-symmetry picture of supervised and unsupervised learning protocols for these Dense Associative Memories: a phase diagram in the space of the control parameters is achieved, independently, both via the Parisi's hierarchy within then replica trick as well as via the Guerra's telescope within the broken-replica interpolation. Further, an explicit analytical investigation is provided to deepen both the big-data and ground state limits of these networks as well as a proof that replica symmetry breaking does not alter the thresholds for learning and slightly increases the maximal storage capacity. Finally the De Almeida and Thouless line, depicting the onset of instability of a replica symmetric description, is also analytically derived highlighting how, crossed this boundary, the broken replica description should be preferred.

cond-mat.dis-nn↗

arXiv2023

Inverse modeling of time-delayed interactions via the dynamic-entropy formalism

Although instantaneous interactions are unphysical, a large variety of maximum entropy statistical inference methods match the model-inferred and the empirically-measured equal-time correlation functions. Focusing on collective motion of active units, this constraint is reasonable when the interaction timescale is much faster than that of the interacting units, as in starling flocks, yet it fails in a number of counter examples, as in leukocyte coordination (where signalling proteins diffuse among two cells). Here, we relax this assumption and develop a path integral approach to maximum-entropy framework, which includes delay in signalling. Our method is able to infer the strength of couplings and fields, but also the time required by the couplings to completely transfer information among the units. We demonstrate the validity of our approach providing excellent results on synthetic datasets of non-Markovian trajectories generated by the Heisenberg-Kuramoto and Vicsek models equipped with delayed interactions. As a proof of concept, we also apply the method to experiments on dendritic migration, where matching equal-time correlations results in a significant information loss.

physics.bio-ph↗

arXiv2023

Parallel Learning by Multitasking Neural Networks

A modern challenge of Artificial Intelligence is learning multiple patterns at once (i.e.parallel learning). While this can not be accomplished by standard Hebbian associative neural networks, in this paper we show how the Multitasking Hebbian Network (a variation on theme of the Hopfield model working on sparse data-sets) is naturally able to perform this complex task. We focus on systems processing in parallel a finite (up to logarithmic growth in the size of the network) amount of patterns, mirroring the low-storage level of standard associative neural networks at work with pattern recognition. For mild dilution in the patterns, the network handles them hierarchically, distributing the amplitudes of their signals as power-laws w.r.t. their information content (hierarchical regime), while, for strong dilution, all the signals pertaining to all the patterns are raised with the same strength (parallel regime). Further, confined to the low-storage setting (i.e., far from the spin glass limit), the presence of a teacher neither alters the multitasking performances nor changes the thresholds for learning: the latter are the same whatever the training protocol is supervised or unsupervised. Results obtained through statistical mechanics, signal-to-noise technique and Monte Carlo simulations are overall in perfect agreement and carry interesting insights on multiple learning at once: for instance, whenever the cost-function of the model is minimized in parallel on several patterns (in its description via Statistical Mechanics), the same happens to the standard sum-squared error Loss function (typically used in Machine Learning).

cond-mat.dis-nn↗

arXiv2023

Statistical Mechanics of Learning via Reverberation in Bidirectional Associative Memories

We study bi-directional associative neural networks that, exposed to noisy examples of an extensive number of random archetypes, learn the latter (with or without the presence of a teacher) when the supplied information is enough: in this setting, learning is heteroassociative -- involving couples of patterns -- and it is achieved by reverberating the information depicted from the examples through the layers of the network. By adapting Guerra's interpolation technique, we provide a full statistical mechanical picture of supervised and unsupervised learning processes (at the replica symmetric level of description) obtaining analytically phase diagrams, thresholds for learning, a picture of the ground-state in plain agreement with Monte Carlo simulations and signal-to-noise outcomes. In the large dataset limit, the Kosko storage prescription as well as its statistical mechanical picture provided by Kurchan, Peliti, and Saber in the eighties is fully recovered. Computational advantages in dealing with information reverberation, rather than storage, are discussed for natural test cases. In particular, we show how this network admits an integral representation in terms of two coupled restricted Boltzmann machines, whose hidden layers are entirely built of by grand-mother neurons, to prove that by coupling solely these grand-mother neurons we can correlate the patterns they are related to: it is thus possible to recover Pavlov's Classical Conditioning by adding just one synapse among the correct grand-mother neurons (hence saving an extensive number of these links for further information storage w.r.t. the classical autoassociative setting).

cond-mat.dis-nn↗