PMPierre-Jean Meyer

Pierre-Jean Meyer

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Pierre-Jean Meyer has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Invariance and symbolic control of cooperative systems for temperature regulation in intelligent buildings

    by Pierre-Jean Meyer

    Invariance et contrôle symbolique de systèmes coopératifs pour la régulation de température dans les bâtiments intelligents: Cette thèse fournit de nouvelles stratégies de contrôle pouvant s'attaquer aux phénomènes hétérogènes et non-linéaires qui décrivent la régulation de la température dans les bâtiments afin d'obtenir un compromis entre le confort et l'efficacité énergétique. Nous nous intéressons donc au contrôle robuste de systèmes coopératifs avec perturbations bornées. Nous résolvons d'abord ce problème grâce à la notion d'intervalle invariant contrôlé robuste, décrivant un ensemble dans lequel l'état peut être maintenu quelle que soit la valeur des perturbations. Une seconde approche décrit des méthodes symboliques pour la synthèse d'un contrôleur discret sur une abstraction finie du système, réalisant une spécification de sûreté associée à l'optimisation des performances. Nous présentons d'abord une méthode symbolique centralisée utilisant les dynamiques du système correspondant au modèle physique. Pour résoudre ses limitations en termes de passage à l'échelle, nous considérons une approche compositionnelle où les méthodes symboliques d'abstraction et de synthèse sont appliquées à des descriptions partielles du système, sous des obligations de type assume-guarantee supposant que la sûreté est satisfaite pour tous les états non-contrôlés. Dans la dernière partie, les contrôleurs présentés sont combinés et évalués dans le cadre d'une régulation de température pour un bâtiment expérimental équipé de la solution UnderFloor Air Distribution.

  • Bridging Neural ODE and ResNet: A Formal Error Bound for Safety Verification

    by Abdelrahman Sayed Sayed, Pierre-Jean Meyer, Mohamed Ghazel


    • 21 May 2025
    • Published by HAL in HAL
    Open Access

    Bridging Neural ODE and ResNet: A Formal Error Bound for Safety Verification

    by Abdelrahman Sayed, Pierre-Jean Meyer, Mohamed Ghazel

    A neural ordinary differential equation (neural ODE) is a machine learning model that is commonly described as a continuousdepth generalization of a residual network (ResNet) with a single residual block, or conversely, the ResNet can be seen as the Euler discretization of the neural ODE. These two models are therefore strongly related in a way that the behaviors of either model are considered to be an approximation of the behaviors of the other. In this work, we establish a more formal relationship between these two models by bounding the approximation error between two such related models. The obtained error bound then allows us to use one of the models as a verification proxy for the other, without running the verification tools twice: if the reachable output set expanded by the error bound satisfies a safety property on one of the models, this safety property is then guaranteed to be also satisfied on the other model. This feature is fully reversible, and the initial safety verification can be run indifferently on either of the two models. This novel approach is illustrated on a numerical example of a fixed-point attractor system modeled as a neural ODE.

  • Monitoring of Neural Network Classifiers Using Neuron Activation Paths

    by Fateh Boudardara, Abderraouf Boussif, Pierre-Jean Meyer, Mohamed Ghazel


  • Open Access

    A review of abstraction methods towards verifying neural networks

    by Fateh Boudardara, Abderraouf Boussif, Pierre-Jean Meyer, Mohamed Ghazel

    Neural networks as a machine learning technique are increasingly deployed in various domains. Despite their performance and their continuous improvement, the deployment of neural networks in safety-critical systems, in particular for autonomous mobility, remains restricted. This is mainly due to the lack of (formal) specifications and verification methods and tools that allow for having sufficient confidence in the behavior of the neural-network-based functions. Recent years have seen neural network verification getting more attention; many verification methods were proposed, yet the practical applicability of these methods to real-world neural network models remains limited. The main challenge of neural network verification methods is related to the computational complexity and the large size of neural networks pertaining to complex functions. As a consequence, applying abstraction methods for neural network verification purposes is seen as a promising mean to cope with such issues. The aim of abstraction is to build an model by omitting some irrelevant details or some details that are not highly impacting w.r.t some considered features. Thus, the verification process is made faster and easier while preserving, to some extent, the relevant behavior regarding the properties to be examined on the original model. In this article, we review both the abstraction techniques for activation functions and model size reduction approaches, with a particular focus on the latter. The review primarily discusses the application of abstraction techniques on feed-forward neural networks and explores the potential for applying abstraction to other types of neural networks. Throughout the article, we present the main idea of each approach and then discuss its respective advantages and limitations in detail. Finally, we provide some insights and guidelines to improve the discussed methods.


  • INNAbstract: An INN-Based Abstraction Method for Large-Scale Neural Network Verification

    by Fateh Boudardara, Abderraouf Boussif, Pierre-Jean Meyer, Mohamed Ghazel

    Neural networks (NNs) have witnessed widespread deployment across various domains, including some safety-critical applications. In this regard, the demand for verifying means of such artificial intelligence techniques is more and more pressing. Nowadays, the development of evaluation approaches for NNs is a hot topic that is attracting considerable interest, and a number of verification methods have been proposed. Yet, a challenging issue for NN verification is pertaining to the scalability when some NNs of practical interest have to be evaluated. This work aims to present INNAbstract , an abstraction method to reduce the size of NNs, which leads to improving the scalability of NN verification and reachability analysis methods. This is achieved by merging neurons while ensuring that the obtained model (i.e., abstract model) overapproximates the original one. INNAbstract supports networks with numerous activation functions. In addition, we propose a heuristic for nodes’ selection to build more precise abstract models, in the sense that the outputs are closer to those of the original network. The experimental results illustrate the efficiency of the proposed approach compared to the existing relevant abstraction techniques. Furthermore, they demonstrate that INNAbstract can help the existing verification tools to be applied on larger networks while considering various activation functions.


  • Open Access

    Reachability Analysis of Neural Networks with Uncertain Parameters

    by Pierre-Jean Meyer

    The literature on reachability analysis methods for neural networks currently only focuses on uncertainties on the network's inputs. In this paper, we introduce two new approaches for the reachability analysis of neural networks with additional uncertainties on their internal parameters (weight matrices and bias vectors of each layer), which may open the field of formal methods on neural networks to new topics, such as safe training or network repair. The first and main method that we propose relies on existing reachability analysis approach based on mixed monotonicity (initially introduced for dynamical systems). The second proposed approach extends the ESIP (Error-based Symbolic Interval Propagation) approach which was first implemented in the verification tool Neurify, and first mentioned in the publication of the tool VeriNet. Although the ESIP approach has been shown to often outperform the mixed-monotonicity reachability analysis in the classical case with uncertainties only on the network's inputs, we show in this paper through numerical simulations that the situation is greatly reversed (in terms of precision, computation time, memory usage, and broader applicability) when dealing with uncertainties on the weights and biases.

  • Interval Weight-Based Abstraction for Neural Network Verification

    by Fateh Boudardara, Abderraouf Boussif, Pierre-Jean Meyer, Mohamed Ghazel


  • Open Access

    Reachability analysis of neural networks using mixed monotonicity

    by Pierre-Jean Meyer

    This paper presents a new reachability analysis approach to compute interval over-approximations of the output set of feedforward neural networks with input uncertainty. We adapt to neural networks an existing mixed-monotonicity method for the reachability analysis of dynamical systems and apply it to each partial network within the main network. This ensures that the intersection of the obtained results is the tightest interval over-approximation of the output of each layer that can be obtained using mixed-monotonicity on any partial network decomposition. Unlike other tools in the literature focusing on small classes of piecewise-affine or monotone activation functions, the main strength of our approach is its generality: it can handle neural networks with any Lipschitz-continuous activation function. In addition, the simplicity of our framework allows users to very easily add unimplemented activation functions, by simply providing the function, its derivative and the global argmin and argmax of the derivative. Our algorithm is compared to five other interval-based tools (Interval Bound Propagation, ReluVal, Neurify, VeriNet, CROWN) on both existing benchmarks and two sets of small and large randomly generated networks for four activation functions (ReLU, TanH, ELU, SiLU).

  • Reachability Analysis of Neural Networks Using Mixed Monotonicity

    by Pierre-Jean Meyer

    This paper presents a new reachability analysis approach to compute interval over-approximations of the output set of feedforward neural networks with input uncertainty. We adapt to neural networks an existing mixed-monotonicity method for the reachability analysis of dynamical systems and apply it to each partial network within the main network. This ensures that the intersection of the obtained results is the tightest interval over-approximation of the output of each layer that can be obtained using mixed-monotonicity on any partial network decomposition. Unlike other tools in the literature focusing on small classes of piecewise-affine or monotone activation functions, the main strength of our approach is its generality: it can handle neural networks with any Lipschitz-continuous activation function. In addition, the simplicity of our framework allows users to very easily add unimplemented activation functions, by simply providing the function, its derivative and the global argmin and argmax of the derivative. Our algorithm is compared to five other interval-based tools (Interval Bound Propagation, ReluVal, Neurify, VeriNet, CROWN) on both existing benchmarks and two sets of small and large randomly generated networks for four activation functions (ReLU, TanH, ELU, SiLU).