Franck VERMET

                                                   Maître de Conférences


Adress :                                                                              E-mail :  franck.vermet@univ-brest.fr
Laboratoire de Mathématiques de Bretagne Occidentale                            
Université de Bretagne Occidentale                                    Office Phone: +33(0)2 98 01 66 56
6, Avenue Victor Le Gorgeu                                               Fax: +33(0)2 98 01 61 28
CS 93837                                                                            Linkedin : Franck Vermet
29238 BREST Cedex 3                                                      Research Gate : Franck Vermet
FRANCE                                                                            Office: N045bis (EURIA)                                                         

Research Interests : 

My research interests are in the area of Probability Theory. More precisely :

  • Statistical Physics, statistical learning, neural networks, associative memory, Hopfield model.
  • Actuarial science.
  • Stochastic algorithms, Monte Carlo methods.
  • Multiuser communication Theory.
  • Random walks.

    • Preprints :

  • A. Charpentier, L. Kouakou, M. Löwe, Ph. Ratz, F. Vermet, Collaborative Insurance Sustainability and Network Structure. (2021) (arXiv:2107.02764)

  • D. Delcaillau, A. Ly, A. Papp, F. Vermet, Model Transparency and Interpretability : Survey and Application to the Insurance Industry. (2020)

  • D. Delcaillau, A. Ly, A. Papp, F. Vermet, Interpretabilité des modèles : état des lieux des méthodes et application à l'assurance. (2020) (arXiv:2007.12919)


    • Research Papers :

  • Th. Giraudon, V. Gripon, M. Löwe, F. Vermet, Towards an Intrinsic Definition of Robustness for a Classifier. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 4015-4019 (2021) (doi: 10.1109/ICASSP39728.2021.9414573) (arXiv:2006.05095) (https://2021.ieeeicassp.org/)

  • P. Papadimitroulas, L. Brocki, N. C. Chung, W. Marchadour, F. Vermet, L. Gaubert, V. Eleftheriadis, D. Plachouris, D. Visvikis, G. C. Kagadis, M. Hatt, Artificial Intelligence: Deep learning in oncological radiomics and challenges of interpretability and data harmonization. Physica Medica, 83, 108-121 (2021) (https://doi.org/10.1016/j.ejmp.2021.03.009)

  • V. Gripon, M. Löwe, F. Vermet, Some Remarks on Replicated Simulated Annealing.   J. Stat. Phys. 182, 51 (2021) (https://doi.org/10.1007/s10955-021-02727-z) (arXiv:2009.14702)

  • M. Löwe, K. Schubert, F. Vermet, Multi-group Binary Choice with Social Interaction and a Random Communication Structure - a Random Graph Approach.   Physica A: Stat. Mech. Appl. 556, 124735 (2020) (arXiv:1904.11890)

  • V. Gripon, G. B. Hacene, M. Löwe, F. Vermet, Improving Accuracy of Nonparametric Transfer Learning via Vector Segmentation.  IEEE ICASSP 2018, 2966-2970 (2018) (arXiv:1710.08637)

  • V. Gripon, M. Löwe, F. Vermet, Associative Memories to Accelerate Approximate Nearest Neighbor Search.  Appl. Sci. 8(9), 1676 (2018) (Open Access)

  • M. Demircigil, J. Heusel, M. Löwe, S. Upgang, F. Vermet, On a model of associative memory with huge storage capacity.  J. Stat. Phys. 168 (2), 288-299 (2017) (arXiv:1702.01929)

  • V. Gripon, J. Heusel, M. Löwe, F. Vermet, A comparative study of sparse associative memories. J. Stat. Phys. 164 (1), 105-129  (2016) (arXiv:1512.08892)
    •  
  • J. Heusel, M. Löwe, F. Vermet, On the capacity of a new model of associative memory based on neural cliques. Stat. & Prob. Lett., 106, 256-261 (2015) (arXiv:1411.1224)

  • M. Löwe, F. Vermet, Capacity of an associative memory model on random graph architectures. Bernoulli 21 (3), 1884-1910 (2015)  (arXiv:1303.4542)

  • M. Ebbers, H. Knöpfel, M. Löwe,  F. Vermet,  Mixing times for the Swapping Algorithm on the Blume-Emery-Griffiths Model. Random Structures & Algorithms 45 (1), 38-77 (2014) (arXiv:1206.4162)

  • C. Wright, R. B. Scott, D. Furnival, P. Ailliot, F. Vermet, Global Observations of Ocean-Bottom Subinertial Current Dissipation. Journal of Physical Oceanography 43 (2), 402-417 (2013)
     
  • M. Löwe,  F. Vermet,  The Hopfield model on a sparse Erdös-Renyi graph.  J. Stat. Phys. 143, 205-214 (2011)

  • M. Löwe, F. Vermet, The swapping algorithm for the Hopfield model with two patterns. Stochastic Process. Appl. 119 (10), 3471-3493 (2009).

  • M. Löwe, F. Vermet, Capacity bounds for the CDMA system and a neural network : a moderate deviations approach.  ESAIM Probab. Stat. 13, 343- 362 (2009).

  • M. Löwe, F. Vermet, The Capacity of q-state Potts neural networks with Parallel Retrieval Dynamics.  Stat. & Prob. Lett. 77, 1505-1514 (2007).

  • R. van der Hofstad, M. Löwe, F. Vermet,  The effect of system load on the existence of bit-errors in CDMA with and without parallel interference cancelation.  IEEE Transactions on Information Theory 52, 4733-4741 (2006).

  • M. Löwe, F. Vermet, The storage capacity of the Hopfield model and moderate deviations. Stat. & Prob. Lett., 75, 237-248 (2005).

  • M. Löwe, F. Vermet, The storage capacity of the Blume-Emery-Griffiths neural network. J. Phys. A : Math. Gen., 38 (16), 3483-3503 (2005)

  • F. Vermet, Phase transition and law of large numbers for a non-symmetric one-dimensional random walk with self-interactions. J. Appl. Prob., 35, 55-63 (1998).

  •  F. Vermet, Transition de phase et vitesse de fuite pour une mesure discrète de Edwards non symétrique sur Z. (French) [Phase transition and escape speed for a nonsymmetric discrete Edwards measure on Z] C. R. Acad. Sci. Paris Sér. I Math. 322 (1996), no. 6, 567-570 (1996)

  • F. Vermet, Discrétisation d'une équation différentielle stochastique dont les coefficients ne dépendent pas du temps et calcul approché d'espérances de fonctionnelles de la solution. (French) [Discretization of a stochastic differential equation whose coefficients are not time-dependent, and rough estimate of the expectations of functionals of the solution] Fascicule de probabilités, 65 pp., Publ. Inst. Rech. Math. Rennes, Univ. Rennes I, Rennes (1992).

  • F. Vermet, Convergence de la variance de l'énergie libre pour le modèle de Hopfield. (French) [Convergence of the variance of the free energy in the Hopfield model] C. R. Acad. Sci. Paris Sér. I Math. 315 (1992), no. 9, 1001-1004 (1992)


    • Books :

  • E. Berthelé, R. Billot, C. Bothorel, M. Habart, J. Janssen, Ph. Lenca, F. Picard, G. Saporta, F. Vermet, Le big data pour les compagnies d'assurance. (French), ISTE Editions, 2017 (ISTE)

  • E. Berthelé, R. Billot, C. Bothorel, M. Habart, J. Janssen, Ph. Lenca, F. Picard, G. Saporta, F. Vermet, Big Data for Insurance companies.  ISTE Editions, 2018 (ISTE)
    •  



      Teaching Supports :

  •  K. Traoré, F. Vermet, Méthodes de provisionnement stochastique. (French), 2017 (Euria-Lab)

  • F. Vermet, Introduction à la simulation stochastique. (French), 2017 (pdf)


    • Habilitation à Diriger des Recherches :

    Etude probabiliste de modèles neuronaux de mémoire associative et d'algorithmes utilisés en physique statistique et data science.  (pdf)
    Université de Bretagne Occidentale, Brest,  France (2019)



    Ph. D. Thesis :

    Etude asymptotique d'un réseau neuronal : le modèle de mémoire associative de Hopfield.
    Université de Rennes 1,  France (1994)
    http://tel.archives-ouvertes.fr/tel-00598243/fr/



    July 20, 2021.