arXiv subjects

Leo D'Amato

Publications and source records attributed to Leo D'Amato.

7 recordsLinked to original sources

arXiv2026

Effects of Social Interactions in Self-Organising Railway Traffic Management

Recent research is exploring self-organised traffic management as a solution for scaling to complex real-world networks. In such a system, trains predict their neighbourhood, produce traffic plan hypotheses, and agree via consensus with neighbours on a future traffic plan to be implemented. This paper investigates a structural parameter within this pipeline: the predictive neighbourhood horizon. The horizon is used by trains to identify future potential conflicts with neighbours, and to establish the local interaction topology, that is, the subset of trains to negotiate with. As the primary design variable, the horizon directly determines the size and density of the social interaction graph, whereas its impact on the complexity of local sub-problems and the distributed consensus dynamics represents a trade-off to be explored. Through a closed-loop simulation framework the study evaluates how variations of the horizon impact the overall decentralised coordination process, from initial conflict detection to distributed schedule consensus. The analysis focuses on investigating the potential trade-off introduced by the horizon choice: balancing local tractability and computational responsiveness with the need for global schedule coherence and feasibility in safety-critical environments. Contrary to intuition, our empirical results indicate that the short time horizons suffice, while long values compromise local tractability and computational responsiveness with no gain in global schedule optimality.

cs.MA↗

arXiv2026

Self-Organizing Railway Traffic Management

Improving traffic management in case of perturbation is one of the main challenges in today's railway research. The great majority of the existing literature proposes approaches to make centralized decisions to minimize delay propagation. In this paper, we propose a new paradigm to the same aim: we design and implement a modular process to allow trains to self-organize. This process consists in having trains identifying their neighbors, formulating traffic management hypotheses, checking their compatibility and selecting the best ones through a consensus mechanism. Finally, these hypotheses are merged into a directly applicable traffic plan. In a thorough experimental analysis on a portion of the Italian network, we compare the results of self-organization with those of a state-of-the-art centralized approach. In particular, we make this comparison mimicking a realistic deployment thanks to a closed-loop framework including a microscopic railway simulator. The results indicate that self-organization achieves better results than the centralized algorithm, specifically thanks to the definition and exploitation of the instance decomposition allowed by the proposed approach.

cs.CY↗

arXiv2026

GENESIS: A Generative Model of Episodic-Semantic Interaction

A central challenge in cognitive neuroscience is to explain how semantic and episodic memory, two major forms of declarative memory, typically associated with cortical and hippocampal processing, interact to support learning, recall, and imagination. Despite significant advances, we still lack a unified computational framework that jointly accounts for core empirical phenomena across both semantic and episodic processing domains. Here, we introduce the Generative Episodic-Semantic Integration System (GENESIS), a computational model that formalizes memory as the interaction between two limited-capacity generative systems: a Cortical-VAE, supporting semantic learning and generalization, and a Hippocampal-VAE, supporting episodic encoding and retrieval within a retrieval-augmented generation (RAG) architecture. GENESIS reproduces hallmark behavioral findings, including generalization in semantic memory, recognition, serial recall effects and gist-based distortions in episodic memory, and constructive episodic simulation, while capturing their dynamic interactions. The model elucidates how capacity constraints shape the fidelity and memorability of experiences, how semantic processing introduces systematic distortions in episodic recall, and how episodic replay can recombine previous experiences. Together, these results provide a principled account of memory as an active, constructive, and resource-bounded process. GENESIS thus advances a unified theoretical framework that bridges semantic and episodic memory, offering new insights into the generative foundations of human cognition.

q-bio.NC↗

arXiv2025

A Rate-Distortion Perspective on the Emergence of Number Sense in Unsupervised Generative Models

Number sense is a core cognitive ability supporting various adaptive behaviors and is foundational for mathematical learning. Here, we study its emergence in unsupervised generative models through the lens of rate-distortion theory (RDT), a normative framework for understanding information processing under limited resources. We train $β$-Variational Autoencoders -- which embody key formal principles of RDT -- on synthetic images containing varying numbers of items, as commonly used in numerosity perception research. We systematically vary the encoding capacity and assess the models' sensitivity to numerosity and the robustness of the emergent numerical representations through a comprehensive set of analyses, including numerosity estimation and discrimination tasks, latent-space analysis, generative capabilities and generalization to novel stimuli. In line with RDT, we find that behavioral performance in numerosity perception and the ability to extract numerosity unconfounded by non-numerical visual features scale with encoding capacity according to a power law. At high capacity, the unsupervised model develops a robust neural code for numerical information, with performance closely approximating a supervised model explicitly trained for visual enumeration. It exhibits strong generative abilities and generalizes well to novel images, whereas at low capacity, the model shows marked deficits in numerosity perception and representation. Finally, comparison with human data shows that models trained at intermediate capacity levels span the full range of human behavioral performance while still developing a robust emergent numerical code. In sum, our results show that unsupervised generative models can develop a number sense and demonstrate that rate-distortion theory provides a powerful information-theoretic framework for understanding how capacity constraints shape numerosity perception.

q-bio.NC↗

arXiv2025

The geometry of efficient codes: how rate-distortion trade-offs distort the latent representations of generative models

Living organisms rely on internal models of the world to act adaptively. These models, because of resource limitations, cannot encode every detail and hence need to compress information. From a cognitive standpoint, information compression can manifest as a distortion of latent representations, resulting in the emergence of representations that may not accurately reflect the external world or its geometry. Rate-distortion theory formalizes the optimal way to compress information while minimizing such distortions, by considering factors such as capacity limitations, the frequency and the utility of stimuli. However, while this theory explains why the above factors distort latent representations, it does not specify which specific distortions they produce. To address this question, here we investigate how rate-distortion trade-offs shape the latent representations of images in generative models, specifically Beta Variational Autoencoders ($β$-VAEs), under varying constraints of model capacity, data distributions, and task objectives. By systematically exploring these factors, we identify three primary distortions in latent representations: prototypization, specialization, and orthogonalization. These distortions emerge as signatures of information compression, reflecting the model's adaptation to capacity limitations, data imbalances, and task demands. Additionally, our findings demonstrate that these distortions can coexist, giving rise to a rich landscape of latent spaces, whose geometry could differ significantly across generative models subject to different constraints. Our findings contribute to explain how the normative constraints of rate-distortion theory shape the geometry of latent representations of generative models of artificial systems and living organisms.

q-bio.NC↗

arXiv2025

Decentralised multi-agent coordination for real-time railway traffic management

The real-time Railway Traffic Management Problem (rtRTMP) is a challenging optimisation problem in railway transportation. It involves the efficient management of train movements while minimising delay propagation caused by unforeseen perturbations due to, e.g, temporary speed limitations or signal failures. This paper re-frames the rtRTMP as a multi-agent coordination problem and formalises it as a Distributed Constraint Optimisation Problem (DCOP) to explore its potential for decentralised solutions. We propose a novel coordination algorithm that extends the widely known Distributed Stochastic Algorithm (DSA), allowing trains to self-organise and resolve scheduling conflicts. The performance of our algorithm is compared to a classical DSA through extensive simulations on a synthetic dataset reproducing diverse problem configurations. Results show that our approach achieves significant improvements in solution quality and convergence speed, demonstrating its effectiveness and scalability in managing large-scale railway networks. Beyond the railway domain, this framework can have broader applicability in autonomous systems, such as self-driving vehicles or inter-satellite coordination.

cs.MA↗

arXiv2023

Neural representation in active inference: using generative models to interact with -- and understand -- the lived world

This paper considers neural representation through the lens of active inference, a normative framework for understanding brain function. It delves into how living organisms employ generative models to minimize the discrepancy between predictions and observations (as scored with variational free energy). The ensuing analysis suggests that the brain learns generative models to navigate the world adaptively, not (or not solely) to understand it. Different living organisms may possess an array of generative models, spanning from those that support action-perception cycles to those that underwrite planning and imagination; namely, from "explicit" models that entail variables for predicting concurrent sensations, like objects, faces, or people - to "action-oriented models" that predict action outcomes. It then elucidates how generative models and belief dynamics might link to neural representation and the implications of different types of generative models for understanding an agent's cognitive capabilities in relation to its ecological niche. The paper concludes with open questions regarding the evolution of generative models and the development of advanced cognitive abilities - and the gradual transition from "pragmatic" to "detached" neural representations. The analysis on offer foregrounds the diverse roles that generative models play in cognitive processes and the evolution of neural representation.

q-bio.NC↗