Job details
Job Type
Temporary
Contract
Full Job DescriptionLe descriptif de l’offre ci-dessous est en Anglais
Type de contrat : CDD
Contrat renouvelable : Oui
Niveau de diplôme exigé : Thèse ou équivalent
Fonction : Post-Doctorant
Contexte et atouts du poste
Environment: We offer a stimulating research environment gathering experts in Neurosciences &
Neuroimaging and experts in Advanced Statistical and Machine Learning methods. The post-doc
position will be available in the context of the Grenoble 3AI project (chair neuromorphometrics @MIAI
https://miai.univ-grenoble-alpes.fr/). The postdoctoral fellow will work in close collaboration with a PhD
student working on Graphs as model for brain network studies and with a Cea-List team which has
developed a bioinspired architecture which could offer interesting resilient properties.
Supervision / contact: GIN-team « Functional neuroimaging and brain perfusion»: Michel Dojat
(michel.dojat@inserm.fr), Inria-team Statify, Sophie Achard (sophie.achard@inria.fr) and CEA LIST Marina
Reyboz (marina.reyboz@cea.fr).
Location:
Grenoble Neurosciences
Institut: https://neurosciences.univ-grenoble-alpes.fr & Inria Montbonnot : https://www.inria.fr/en/teams/mistis
Starting date: Autumn 2021
Mission confiée
Proposal description:
Graphs are nowadays a common mathematical formalism used in various domains where the notion of
network is significant, such as Genetics, Sociology, Ecology and Neurosciences for instance. For the
latter graph representation allows to describe brain connectivity both at a structural and a functional
level (1). Moreover, graph neural network is an emerging topic in data mining where the graph modelling
allows the use of mathematical tools from graph theory in combination with deep learning approach.
The objective of this Post-Doctoral position is to use mathematical properties of classical graph neural
networks in order to explore unresolved specific weaknesses of deep neural networks (DNN). We will
focus on catastrophic forgetting (or catastrophic interference) and adversarial attack. The former
hampers the training phase of DNN when the trained model forgets a previously learned pattern when
confronted with new examples to learn. The latter refers to the vulnerability of DNN to a subtle carefully
designed change in how inputs are presented completely alters its output and leads to wrong conclusion.
To study these major DNN drawbacks notably for medical application (2), we propose to represent the
DNN as a graph and track learning and prediction under different conditions of training and attack (3).
The final goals are to respond to several questions: are specific hidden neurons (or layers) vulnerable
to forgetting or attack? Which solutions can be implemented (introduction of penalty during the training
phase, specific architectures including feedback connections, ...) to design DNN more resilient to
forgetting and attack?
(1)
Hanczar, B., Zehraoui, F., Issa, T. et al. (2020) Biological interpretation of deep neural network for phenotype predic-
tion based on gene expression. BMC Bioinformatics 21, 501.
(2)
Finlayson, S.G., Bowers, J.D., Ito, J., Zittrain, J.L., Beam, A.L., and Kohane, I.S. (2019). Adversarial attacks on med-
ical machine learning. Science 363, 1287-1289.
(3)
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K., & Samek, W. (2015). On Pixel-Wise Explanations for
Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation. PLoS ONE, 10.
Principales activités
Proposal description:
Graphs are nowadays a common mathematical formalism used in various domains where the notion of
network is significant, such as Genetics, Sociology, Ecology and Neurosciences for instance. For the
latter graph representation allows to describe brain connectivity both at a structural and a functional
level (1). Moreover, graph neural network is an emerging topic in data mining where the graph modelling
allows the use of mathematical tools from graph theory in combination with deep learning approach.
The objective of this Post-Doctoral position is to use mathematical properties of classical graph neural
networks in order to explore unresolved specific weaknesses of deep neural networks (DNN). We will
focus on catastrophic forgetting (or catastrophic interference) and adversarial attack. The former
hampers the training phase of DNN when the trained model forgets a previously learned pattern when
confronted with new examples to learn. The latter refers to the vulnerability of DNN to a subtle carefully
designed change in how inputs are presented completely alters its output and leads to wrong conclusion.
To study these major DNN drawbacks notably for medical application (2), we propose to represent the
DNN as a graph and track learning and prediction under different conditions of training and attack (3).
The final goals are to respond to several questions: are specific hidden neurons (or layers) vulnerable
to forgetting or attack? Which solutions can be implemented (introduction of penalty during the training
phase, specific architectures including feedback connections, ...) to design DNN more resilient to
forgetting and attack?
(1)
Hanczar, B., Zehraoui, F., Issa, T. et al. (2020) Biological interpretation of deep neural network for phenotype predic-
tion based on gene expression. BMC Bioinformatics 21, 501.
(2)
Finlayson, S.G., Bowers, J.D., Ito, J., Zittrain, J.L., Beam, A.L., and Kohane, I.S. (2019). Adversarial attacks on med-
ical machine learning. Science 363, 1287-1289.
(3)
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K., & Samek, W. (2015). On Pixel-Wise Explanations for
Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation. PLoS ONE, 10.
Avantages- Subsidized meals
- Partial reimbursement of public transport costs
- Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
- Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage
En cliquant sur "JE DÉPOSE MON CV", vous acceptez nos CGU et déclarez avoir pris connaissance de la politique de protection des données du site jobijoba.com.