arXiv subjects

Cristian Versari

Publications and source records attributed to Cristian Versari.

4 recordsLinked to original sources

arXiv2026

Abstract Simulation of Reaction Networks

Reaction networks model reactions between a finite set of species. These networks can be associated with different semantics, depending on the type of analysis and the phenomena under study. The standard continuous semantics is given by a system of differential equations based on the kinetic expressions of the reactions. To simulate a network under this semantics, the full knowledge of the kinetic laws of each reaction and the initial concentrations of each species is necessary. Since in empirical settings the quantitative information about the reactions can be partially or totally unknown, the challenge is to introduce new semantics that can still be applied. In this direction, a recent approach in the state of the art concerning Reaction Networks proposes a qualitative abstraction that is too coarse to properly capture the time-course continuous behaviour. Starting from the ideas of this approach, in this paper we first introduce the causal continuous semantics for Reaction Networks to capture their continuous-time dynamics, preserving the causality hidden inside each transition. Later, we introduce the differential sign semantics to abstract in a qualitative way the behaviour of a system under the causal continuous semantics. We show that our new method, based on abstract interpretation, yields appropriate Boolean transition graphs that refine those provided by the previous approach.

cs.DM↗

arXiv2023

Self-mentoring: a new deep learning pipeline to train a self-supervised U-net for few-shot learning of bio-artificial capsule segmentation

Background: Accurate segmentation of microscopic structures such as bio-artificial capsules in microscopy imaging is a prerequisite to the computer-aided understanding of important biomechanical phenomenons. State-of-the-art segmentation performances are achieved by deep neural networks and related data-driven approaches. Training these networks from only a few annotated examples is challenging while producing manually annotated images that provide supervision is tedious. Method: Recently, self-supervision, i.e. designing a neural pipeline providing synthetic or indirect supervision, has proved to significantly increase generalization performances of models trained on few shots. The objective of this paper is to introduce one such neural pipeline in the context of micro-capsule image segmentation. Our method leverages the rather simple content of these images so that a trainee network can be mentored by a referee network which has been previously trained on synthetically generated pairs of corrupted/correct region masks. Results: Challenging experimental setups are investigated. They involve from only 3 to 10 annotated images along with moderately large amounts of unannotated images. In a bio-artificial capsule dataset, our approach consistently and drastically improves accuracy. We also show that the learnt referee network is transferable to another Glioblastoma cell dataset and that it can be efficiently coupled with data augmentation strategies. Conclusions: Experimental results show that very significant accuracy increments are obtained by the proposed pipeline, leading to the conclusion that the self-supervision mechanism introduced in this paper has the potential to replace human annotations.

cs.CV↗

arXiv2022

SODA: Self-organizing data augmentation in deep neural networks -- Application to biomedical image segmentation tasks

In practice, data augmentation is assigned a predefined budget in terms of newly created samples per epoch. When using several types of data augmentation, the budget is usually uniformly distributed over the set of augmentations but one can wonder if this budget should not be allocated to each type in a more efficient way. This paper leverages online learning to allocate on the fly this budget as part of neural network training. This meta-algorithm can be run at almost no extra cost as it exploits gradient based signals to determine which type of data augmentation should be preferred. Experiments suggest that this strategy can save computation time and thus goes in the way of greener machine learning practices.

stat.ML↗

arXiv2010

A Process Calculus for Expressing Finite Place/Transition Petri Nets

We introduce the process calculus Multi-CCS, which extends conservatively CCS with an operator of strong prefixing able to model atomic sequences of actions as well as multiparty synchronization. Multi-CCS is equipped with a labeled transition system semantics, which makes use of a minimal structural congruence. Multi-CCS is also equipped with an unsafe P/T Petri net semantics by means of a novel technique. This is the first rich process calculus, including CCS as a subcalculus, which receives a semantics in terms of unsafe, labeled P/T nets. The main result of the paper is that a class of Multi-CCS processes, called finite-net processes, is able to represent all finite (reduced) P/T nets.

cs.LO↗