Article separation in historical newspapers Interested in joining a young group the crossroad between document analysis and NLP, located in a historical town by the Atlantic Ocean? And walk 10 minutes from the lab to the beach
. We have open positions in the context of 2 ongoing Horizon 2020 projects: Embeddia and NewsEye as well as subsequent projects. In 2020-2021, we have among others published long papers in CORE A* and A conferences ACL, JCDL, ICDAR, CoNLL, DAS COLING, ICADL..
We coordinate the H2020 NewsEye project, focused on improving access to large European collections of historical newspapers.
We developed the NewsEye platform for navigating through such collections, a platform it will build upon in future years.
Full details on the NewsEye project are available on its website - http://newseye.eu/
Location: L3i laboratory, La Rochelle, France
Duration: 2 years (1+1), with possible further extension
Net salary range: 2100€-2300 € monthly
Context: H2020 NewsEye project and regional project Anna
Keywords: digitized documents, combination of visual and textual features, layout analysis, statistical NLP, language-independent approaches, deep/machine learning.
Applications are invited for a postdoctoral researcher position on the separation of articles from digitized newspapers, in particular historical newspapers. This task is a critical first step for any use of digitized newspapers, which are initially only split per “page image” files.
Your goal will be to study the state of the art and devise methods combining visual and textual features so as improve the performance of article separation on a large scale. In particular, we seek for methods that function with limited training data and for several languages. NLP and image analysis experience are equally valued. Experience of both is ideal.
Who we search for: - PhD in document analysis, NLP, IR, or ML, ideally followed by postdoctoral experience
- proven record of high-level publications in one or more of those fields
- fluency in written and spoken English (French language skills are not relevant)
Applications including a CV and a one-page research statement discussing how the candidate's background fits requirements and topic are to be sent to by email to [email protected], strictly with the subject "NewsEye/ANNA postdoc application".
Application deadline: 13 October 2021.
Cross-lingual and cross-domain terminology alignment
Interested in joining a young NLP group of 10+ people located in a historical town by the Atlantic Ocean? And walk 10 minutes from the lab to the beach.
We have open positions in the context of 2 ongoing Horizon 2020 projects: Embeddia and NewsEye as well as related projects.
In 2020-2021, we have among others published long papers in CORE A* and A conferences ACL, JCDL, CoNLL, ICDAR, COLING, ICADL, etc.
Location: L3i laboratory, La Rochelle, France
Duration: 2 years (1+1), with possible further extension
Net salary range: 2100€-2300 € monthly
Context: H2020 Embeddia project and regional project Termitrad
Start: 1 January 2022
Keywords: terminology alignment, cross-lingual word embeddings, named-entity recognition and linking, deep/machine learning, statistical NLP, (text) mining.
Applications are invited for a postdoctoral researcher position around the topic of project Termitrad: keyword and terminology alignment 1) across languages and 2) across domains.
In short, the overall objective of the project is to improve the relevance of the keywords describing research papers (and, time allowing, the quality of abstracts).
One the one hand (cross-lingual alignment), we will rely on a corpora of journal articles with both French and English keywords and abstracts, both in as written by authors and in versions curated by experts.
On the other hand (crossdomain alignment), we will work with use cases provided by researchers from different fields using different terms to describe similar concepts.
To address this very project, the project team will consist of senior staff, 2 post-doctoral researchers and 2-3 PhD students, one of which is jointly supervised in the Józef Stefan Institute in Ljubljana, coordinator of H2020 Embeddia.
In this context, you will first be in charge of building a state of the art of existing related approaches, tools and resources, then to conduct further research and experiments, as well as participate in the supervision of PhD students.
Who we search for: - PhD in statistical NLP, IR, or ML, ideally with further postdoctoral experience
- proven record of high-level publications in one or more of those fields
- fluency in written and spoken English (French language skills are irrelevant)
Applications including a CV and a one-page research statement discussing how the candidate's background fits requirements and topic are to be sent to by email to [email protected], strictly with the subject "Embeddia/Termitrad postdoc application".
Application deadline: 13 October 2021.
Location and unit: CEA LSPS
Located in the south of France (Marcoule), the Process Simulation and Systems Analysis Laboratory aims at:
- the simulation of processes in stationary or dynamic state. These simulations aim at defining a process diagram, estimating its performance, sizing the equipment, but also assessing incident scenarios (safety studies) and analysing malfunctions.
- defining process diagrams and carrying out scenario studies, backed by technical-economic evaluations and preliminary waste stream estimates, with a view to guide process choices.
The project needs to have close interactions with another CEA entities, CEA ISAS and CEA LIST.
Located in Saclay, south of Paris, CEA LIST (http://www-list.cea.fr/) is a scientific and technological research center dedicated to the development of software, embedded systems and sensors for applications such as defense, security, energy, nuclear power, the environment and health.
Within this institute, the SID (Data Intelligence Service) works on algorithms and methodologies for artificial intelligence and signal processing.
The laboratory's research and technological advances are guided by a variety of applications, for which the specificities and constraints on the data or the execution environment require a fine design of AIs and their integration as the unitary bricks of complex systems.
This entity takes part of this project only to connect it to the neural network developments.
Project description The postdoctoral fellow will join an internal project shared between different CEA entities.
The aim is to develop algorithms able to take into account the uncertainty in the learning database of neural networks. Indeed, the database can contain simulated data as well as real data.
By definition, the simulated data is impacted by the uncertainty of the model used for the calculation and the real data is impacted by the uncertainty of the measuring instrument. In this postdoctoral research, we focus only on the uncertainty of real data and we suppose that the simulated data is exact.
The aim is to take into account such information in the building process of the neural network.
Qualifications 1. PhD in machine learning from an accredited university
2. Excellent communication skills, both verbal and written in English
3. Skills in Python language
4. Communication skills in French
5. Experience in uncertainty estimation
6. Experience in physics application is a plus
Salary & benefits
The salary will depend on the applicant’s profile and experience. The position comes with various social benefits (e.g. health insurance).
This position is open for one year.
Application and contacts
To apply send an updated CV and a motivation letter to:
Amandine DUTERME ([email protected])
Fabrice GAUDIER ([email protected])
Laurence CORNEZ ([email protected])
The position is open immediately (November 2021). Review of applications will begin as soon as applications are received and continue until the position is filled or the deadline of January 1st 2022 is reached.
The Institut de Recherche en informatique de Toulouse (IRIT-Toulouse University) has a 12 months position offer within the STERHEOTYPES project (https://www.irit.fr/sterheotypes/), a three years (2021-2024) funded project under the “Challenge for Europe”, on using NLP for the detection of racial stereotypes in social media content.
The project focuses on ‘racial hoaxes’, communicative acts created to circulate information that are an allegation of a threat posed against someone’s health or safety associated to individual or a group because of race, ethnicity or religion.
Aiming at understanding the social and psychological processes emerging from racial hoaxes in digital generations across three border Mediterranean European countries (Italy, Spain and France), the project integrates different methodological approaches coming from psychology and computational linguistics.
The candidate will investigate racial stereotype detection in tweets and will focus in particular on: (1) Developing deep learning models for an accurate identification of stereotypes and their characterization, (2) Exploring multilingual detection in collaboration with other partners from Italy (Univ. Torino, Univ. Bari) and Spain (Univ. Barcelona).
**Additional information** --> Duration of the position: 12 months
--> Salary : between 2400 euros and 2700 euros (after taxes) depending on experience.
--> Starting date: January or February 2022
--> Location : IRIT, Université Paul Sabatier, Toulouse.
**Ideal Candidate**
-->PhD in Computational Linguistics
--> A very good experience in deep learning approaches for NLP
--> Good programming skills in Python
--> Good experience in hate speech detection.
**Application** Send your CV together with a list of publications and a statement of research interests to Farah Benamara ([email protected]) and Véronique Moriceau ([email protected]) before ***31th of October 2021***
-- ======================== Farah Benamara Zitoune
Associate Professor HDR, Université Paul Sabatier IRIT-CNRS
118 Route de Narbonne, 31062, Toulouse.
Tel : +33 5 61 55 77 06
http://www.irit.fr/~Farah.Benamara ==================================
Internship offer--//
- Title: Evaluation of lexical embeddings based on graphs by extrinsic methods
- The offer in detail : https://lium.univ-lemans.fr/evaluation-des-plongements-lexicaux-bases-graphes-par-des-methodes-extrinseques/
- Level: Master
- Gratuity: Yes
- Duration: 5 to 6 months
- Start: as soon as possible from February
- Host team: LIUM - LST
- Location: Le Mans
- Supervisor (s): Nicolas Dugué
- Context: As part of the ANR DIGING project
- Thesis: Funding available to pursue a doctorate
# Keywords: Lexical embeddings, automatic language processing, graphs, interpretability, ethics, green computing.
@Contact : nicolas.dugue (at) univ-lemans.fr
Regards - Nicolas Dugué
Lecturer / Assistant Professor
https://lium.univ-lemans.fr/team/nicolas-dugue/
LIUM , LST and EIAH / Language and Speech Technology team
Coordinator of the ANR DIGING project: candidate research Internship -> Thesis on the project
Referent Music and Sport studies IUT GEA
06.16.42.24. 89
Avenue Olivier Messiaen, 72085 - LE MANS Cedex 09
Title: * Evaluation of lexical embeddings based on graphs by extrinsic methods
* - The offer in detail *: https://lium.univ-lemans.fr/evaluation-des-plongements-lexicaux-bases-graphes-par-des-methodes-extrinseques/
* - Level: * Master
* - Gratuity: * Yes
* - Duration: * 5 to 6 months
* - Start: * as soon as possible from February
* - Reception team: * LIUM - LST
* - Location: * Le Mans
* - Supervisor (s): * Nicolas Dugué
* - Context: * As part of the ANR DIGING project https://lium.univ-lemans.fr/diging/
* - Thesis: * Funding available to pursue a doctorate
* # Keywords: * Lexical embeddings, automatic processing of the language, graphs, interpretability, ethics, green computing.
* @ Contact: * nicolas.dugue (at) univ-lemans.fr Regards
JOB / JOB OFFER *
* 12-month postdoctoral fellowship (100%). *
Profile: History of the French language and TAL
When: 01/01/2022.
Where: Grenoble Alpes University, LiDiLEM laboratory (France)
Grenoble Alpes University: https://www.univ-grenoble-alpes.fr/
LiDiLEM laboratory (axis 1): https://lidilem.univ-grenoble-alpes.fr/
* Project: ** Phraseo 13-18. Phraseology and stylistics in the novel old regime (13th-18th centuries) *
The project is part of the field of digital humanities using the methods of tooled corpus linguistics. Its originality lies in its dual synchronic and diachronic approach to study phraseological phenomena in the long term, from the old French to classical French.
By responding to a problem currently in full emergence, the results will help to refine an operative theory of textual genres, the category of genre being traditionally used to group texts by reducing their variability. The linguistic study of phraseological units is one keys that will allow us to respond to this problem.
This multidisciplinary research presupposes working closely collaboration with specialists in Automatic Treatment of Languages (NLP) but also to use linguistic methods and stylistic for data interpretation. Its aim is to to constitute original corpus of novels in diachrony and to bring new theoretical knowledge.
This project is part of the “Phraseology in diachrony” action (see LiDiLEM website).
Application deadline: November 7, 2021 midnight.
Cover letter + detailed CV.
Job description on request.
Contact: [email protected]
https://euraxess.ec.europa.eu/jobs/685980
* Postdoctoral researcher 12 months (full time) *
Profile: History of French language and NLP
When: 01/01/2022
Where: Grenoble Alpes University, LiDiLEM laboratory (France)
Grenoble Alpes University: https://www.univ-grenoble-alpes.fr/
LiDiLEM laboratory (axis 1): https://lidilem.univ-grenoble-alpes.fr/
The * project / “/ ** Phraseo 13-18. Phraseology and stylistics in the ancient regime novel (13th-18th centuries) ** ”* is part of the Digital Humanities field and uses the methods of corpus linguistics.
Its originality lies in its both synchronic and diachronic approach to study phraseological phenomena over time, from Old French to Classical French.
By answering a problematic currently in full emergence, the results will contribute to refine an operational theory of the textual genres, the category of genre being traditionally used to group texts by reducing their variability. The linguistic study of phraseological units is one of the keys to answering this problem.
This multidisciplinary research implies working in close collaboration with specialists in NLP but also using linguistic and stylistic methods to interpret the data. Its objective is to constitute diachronic corpora of literary fiction and to bring new theoretical knowledge.
Our project takes place into the action "Phraseology in diachrony" (see on the LiDiLEM website).
* How to apply * Deadline: 07/11/2021 midnight.
Covering letter + detailed CV.
Job description on request.
Contact: [email protected]
https://l3i.univ-larochelle.fr/spip.php?action=acceder_document&arg=1662&cle=a52b83c3c660824278f7ffe92ee4bb5c47ac9fde&file=pdf%2Fpostdoc-articleseparation_cle0614a1.pdf
Article separation in historical newspapers
Interested in joining a young group the crossroad between document analysis and NLP, located in a historical town by the Atlantic Ocean? And walk 10 minutes from the lab to the beach.
We have open positions in the context of 2 ongoing Horizon 2020 projects: Embeddia and NewsEye as well as subsequent projects.
In 2020-2021, we have among others published long papers in *CORE A* and A* conferences ACL, JCDL, ICDAR, CoNLL, DAS COLING, ICADL..
We coordinate the H2020 NewsEye project, focused on improving access to large European collections of historical newspapers. We developed the *NewsEye platform* for navigating through such collections, a platform it will build upon in future years.
Full details on the NewsEye project are available on its website - http://newseye.eu/
*Location*: L3i laboratory, La Rochelle, France
*Duration*: 2 years (1+1), with possible further extension
*Net salary range*: 2100€-2300 € monthly
*Context*: H2020 NewsEye project and regional project Anna
Keywords: *digitized documents, combination of visual and textual features, layout analysis, statistical NLP, language-independent approaches, deep/machine learning.*
Applications are invited for a postdoctoral researcher position on the separation of articles from digitized newspapers, in particular historical newspapers.
This task is a critical first step for any use of digitized newspapers, which are initially only split per “page image” files.
Your goal will be to study the state of the art and devise methods combining visual and textual features so as improve the performance of article separation on a large scale.
In particular, we seek for methods that function with limited training data and for several languages.
NLP and image analysis experience are equally valued. Experience of both is ideal.
Who we search for: - PhD in document analysis, NLP, IR, or ML, ideally followed by postdoctoral experience
- proven record of high-level publications in one or more of those fields
- fluency in written and spoken English (French language skills are not relevant)
Applications including a CV and a one-page research statement discussing how the candidate's background fits requirements and topic are to be sent to by email to [email protected], strictly with the subject "NewsEye/ANNA postdoc application".
Application deadline: 13 October 2021.
https://l3i.univ-larochelle.fr/spip.php?action=acceder_document&arg=1662&cle=a52b83c3c660824278f7ffe92ee4bb5c47ac9fde&file=pdf%2Fpostdoc-articleseparation_cle0614a1.pdf
https://l3i.univ-larochelle.fr/spip.php?action=acceder_document&arg=1663&cle=9cdd6bde3a5ff4d4b148201051594ccaf6fe5b7e&file=pdf%2Fpostdoc-crosslingual-crossdomain-termalignment_cle4ceb14.pdf
*Cross-lingual and cross-domain terminology alignment*
Interested in joining a young NLP group of 10+ people located in a historical town by the Atlantic Ocean? And walk 10 minutes from the lab to the beach. We have open positions in the *context of 2 ongoing Horizon 2020* projects: Embeddia and NewsEye as well as related projects. In 2020-2021, we have among others published long papers in *CORE A* and A* conferences ACL, JCDL, CoNLL, ICDAR, COLING, ICADL, etc.
*Location*: L3i laboratory, La Rochelle, France
*Duration*: 2 years (1+1), with possible further extension
*Net salary range*: 2100€-2300 € monthly
*Context*: H2020 Embeddia project and regional project Termitrad
*Start*: 1 January 2022
Keywords: *terminology alignment, cross-lingual word embeddings, named-entity recognition and linking, deep/machine learning, statistical NLP, (text) mining*.
Applications are invited for a postdoctoral researcher position around the topic of project Termitrad: keyword and terminology alignment 1) across languages and 2) across domains. In short, the overall objective of the project is to improve the relevance of the keywords describing research papers (and, time allowing, the quality of abstracts).
One the one hand (cross-lingual alignment), we will rely on a corpora of journal articles with both French and English keywords and abstracts, both in as written by authors and in versions curated by experts. On the other hand (crossdomain alignment), we will work with use cases provided by researchers from different fields using different terms to describe similar concepts.
To address this very project, the project team will consist of senior staff, 2 post-doctoral researchers and 2-3 PhD students, one of which is jointly supervised in the Józef Stefan Institute in Ljubljana, coordinator of H2020 Embeddia.
In this context, you will first be in charge of building a state of the art of existing related approaches, tools and resources, then to conduct further research and experiments, as well as participate in the supervision of PhD students.
Who we search for: - PhD in statistical NLP, IR, or ML, ideally with further postdoctoral experience
- proven record of high-level publications in one or more of those fields
- fluency in written and spoken English (French language skills are irrelevant)
Applications including a CV and a one-page research statement discussing how the candidate's background fits requirements and topic are to be sent to by email to [email protected], strictly with the subject "Embeddia/Termitrad postdoc application".
*Application deadline: 13 October 2021.*
PDF version of this call- https://l3i.univ-larochelle.fr/spip.php?action=acceder_document&arg=1663&cle=9cdd6bde3a5ff4d4b148201051594ccaf6fe5b7e&file=pdf%2Fpostdoc-crosslingual-crossdomain-termalignment_cle4ceb14.pdf
The Institut de Recherche en informatique de Toulouse (IRIT-Toulouse University) has a 12 months position offer within the STERHEOTYPES project (https://www.irit.fr/sterheotypes/), a three years (2021-2024) funded project under the “Challenge for Europe”, on using NLP for the detection of racial stereotypes in social media content.
The project focuses on ‘racial hoaxes’, communicative acts created to circulate information that are an allegation of a threat posed against someone’s health or safety associated to individual or a group because of race, ethnicity or religion.
Aiming at understanding the social and psychological processes emerging from racial hoaxes in digital generations across three border Mediterranean European countries (Italy, Spain and France), the project integrates different methodological approaches coming from psychology and computational linguistics.
The candidate will investigate racial stereotype detection in tweets and will focus in particular on:
(1) Developing deep learning models for an accurate identification of stereotypes and their characterization,
(2) Exploring multilingual detection in collaboration with other partners from Italy (Univ. Torino, Univ. Bari) and Spain (Univ. Barcelona).
**Additional information**
--> Duration of the position: 12 months
--> Salary : between 2400 euros and 2700 euros (after taxes) depending on experience.
--> Starting date: January or February 2022
--> Location : IRIT, Université Paul Sabatier, Toulouse.
**Ideal Candidate** --> PhD in Computational Linguistics
--> A very good experience in deep learning approaches for NLP
--> Good programming skills in Python
--> Good experience in hate speech detection.
**Application** Send your CV together with a list of publications and a statement of research interests to
Farah Benamara ([email protected]) and
Véronique Moriceau ([email protected]) before
***31th of October 2021***
Post-doctoral position: Deep Learning for opinion mining in human testimonials related to industrial accident
The Machine Learning team at the LITIS laboratory, the computer science laboratory of the University of Rouen Normandy, is looking for a post-doctoral researcher on a 18-months contract, starting as soon as possible.
The position will be financed by the ANR research project CATCH (french acronym for "Automatic Understanding of Human Sensors Testimonials"), which involves the R&D center of the company Saagie, specialized in B2B DataOps solutions, Atmo Normandie, one of the approved French air quality monitoring associations and LITIS.
Location : LITIS lab., University of Rouen Normandy, Rouen, France
Duration : 18-months, starting as soon as possible
Salary : ~2100€ / month (before income tax), including social security coverage in line with French regulations
Applications : open from 01/09/2021 to 31/12/2021
Keywords: Deep learning – Natural Langage Processing – Sentiment Analysis / Opinion Mining
Scientific context: The ambition of the CATCH project is to propose artificial intelligence and deep learning tools to take into account and automatically exploit the multitude of human testimonies related to an industrial accident and its consequences on the environment and health. By involving the population in the collection and analysis of data, particularly through social networks, and by providing effective means for interpreting this data, the proposed solution should contribute to providing answers to the worrying problem of industrial accidents and their consequences.
The overall objective is first to draw up a precise cartography of the nuisances in order to follow the propagation and the evolution of the phenomena in time, and then to analyze and characterize the sentiment of the population and its evolution throughout the crisis. To do so, we intend to exploit testimonials collected on the ODO platform of Atmo Normandie, which combines these testimonies with geographical information, in conjonction with data extracted from the micro-blogging platform Twitter. Since these data are primarily texts, state-of-the-art approaches from the Natural Language Processing (NLP) field are favored, in particular, self-supervised deep learning methods such as Transformers that are known to be the most performant today for a wide range of NLP tasks.
Research goals:
The objective of this research work is twofold:
1. The automatic generation of a map of nuisances around the site of an industrial incident to monitor the propagation and the evolution of the phenomena over time.
2. The automatic recognition of the population's perception and its evolution throughout the crisis.
Related to these tasks, the post-doctoral researcher will be in charge of proposing solution for:
• extracting and linking twitter data with testimonials from the ODO dataset, which is fully labelled and associates textual testimonies with geographical data. The interest in establishing this link is to be able to enrich the data from the ODO platform to refine the mapping of nuisances in real time. This could be achieved for example, by using pseudo-labelling techniques1 or Constrative Representation Learning methods which have recently been applied to text data2.
• detecting in all the testimonials collected from Twitter or from the ODO platform, the presence (or absence) of several pre-identified emotions (e.g. surprise, fear, anger, sadness, disgust, etc.), several of which can be expressed at the same time.
This research work will therefore involve being familiar with the state-of-the-art NLP deep learning methods and in particular with their applications to sentiment analysis and opinion mining tasks. It will also require experience with the use and exploitation of data from Twitter in a data science context.
Application:
The successful applicant will:
• possess or be in the process of obtaining a Ph.D. in computer science or applied mathematics, with a focus on machine learning or data mining.
• have strong programming skills (Java, Python, etc.) and in-depth understanding of statistics and machine learning.
• have already worked with deep learning architecture dedicated to texts (RNNs, Transformers, etc.) and/or images (CNNs, FCNs, GANs).
• have a productive publication record.
Your application should include:
• curriculum vitae
• statement of past research accomplishments, career goal and how this position will help you achieve your goals
• two representative publications
• contact information for at least two references
Contact
Application must be sent to :
• Simon BERNARD, University of Rouen Normandy, [email protected]
• Clément CHATELAIN, INSA Rouen Normandy, [email protected]
• Alexandre PAUCHET, INSA Rouen Normandy, [email protected]
Location and unit: CEA LIST/ SID
Located in Saclay, south of Paris, CEA LIST (http://www-list.cea.fr/) is a scientific and technological research center dedicated to the development of software, embedded systems and sensors for applications such as defense, security, energy, nuclear power, the environment and health.
CEA LIST is part of the dynamic and stimulating ecosystem of the University of Paris-Saclay - the largest French scientific center with 60,000 students.
It has more than 700 researchers focusing on intelligent digital systems, centered around artificial intelligence, the factory of the future, innovative instrumentation, cyber-physical systems and digital health.
Within this institute, the SID (Data Intelligence Service) works on algorithms and methodologies for artificial intelligence and signal processing.
The laboratory's research and technological advances are guided by a variety of applications, for which the specificities and constraints on the data or the execution environment require a fine design of AIs and their integration as the unitary bricks of complex systems.
The project needs to have close interactions with another CEA entity, CEA Marcoule.
Located in the south of France, the Process Simulation and Systems Analysis Laboratory aims at:
- the simulation of processes in stationary or dynamic state. These simulations aim at defining a process diagram, estimating its performance, sizing the equipment, but also assessing incident scenarios (safety studies) and analysing malfunctions.
- defining process diagrams and carrying out scenario studies, backed by technical-economic evaluations and preliminary waste stream estimates, with aiming at guiding process choices.
Project description The postdoctoral fellow will join an internal project shared between two CEA entities.
The aim is to develop an algorithm with different machine learning technics (neural networks and active learning) able to estimate the operational parameters of a liquid-liquid extraction process.
Indeed, the state of an industrial chemical process is accessible through operating parameters and available monitoring measures.
Such information is essential to detect and evaluate operational changes in order to keep the process as close as possible to the target state.
Qualifications
1. PhD in machine learning from an accredited university
2. Excellent communication skills, both verbal and written in English
3. Programmation in Python language (Tensorflow will be used)
4. Communication skills in French
5. Experience in convolutional network using times series is a plus
6. Experience in physics application is a plus
Salary & benefits
The salary will depend on the applicant’s profile and experience. The position comes with various social benefits (e.g. health insurance).
This position is open for one year, renewable once.
Application and contacts
To apply send an updated CV and a motivation letter to:
Laurence CORNEZ ([email protected])
Binh DINH ([email protected])
Amandine DUTERME ([email protected])
Stéphane GAZUT ([email protected])
The position is open immediately (October 2021). Review of applications will begin as soon as applications are received and continue until the position is filled.
Location and unit: CEA LSPS
Located in the south of France (Marcoule), the Process Simulation and Systems Analysis Laboratory aims at:
- the simulation of processes in stationary or dynamic state. These simulations aim at defining a process diagram, estimating its performance, sizing the equipment, but also assessing incident scenarios (safety studies) and analysing malfunctions.
- defining process diagrams and carrying out scenario studies, backed by technical-economic evaluations and preliminary waste stream estimates, with a view to guide process choices.
The project needs to have close interactions with another CEA entities, CEA ISAS and CEA LIST.
Located in Saclay, south of Paris, CEA LIST (http://www-list.cea.fr/) is a scientific and technological research center dedicated to the development of software, embedded systems and sensors for applications such as defense, security, energy, nuclear power, the environment and health.
Within this institute, the SID (Data Intelligence Service) works on algorithms and methodologies for artificial intelligence and signal processing.
The laboratory's research and technological advances are guided by a variety of applications, for which the specificities and constraints on the data or the execution environment require a fine design of AIs and their integration as the unitary bricks of complex systems.
This entity takes part of this project only to connect it to the neural network developments.
Project description
The postdoctoral fellow will join an internal project shared between different CEA entities.
The aim is to develop algorithms able to take into account the uncertainty in the learning database of neural networks.
Indeed, the database can contain simulated data as well as real data. By definition, the simulated data is impacted by the uncertainty of the model used for the calculation and the real data is impacted by the uncertainty of the measuring instrument.
In this postdoctoral research, we focus only on the uncertainty of real data and we suppose that the simulated data is exact.
The aim is to take into account such information in the building process of the neural network. The project fits into the context of the dynamic state estimation of liquid-liquid extraction and benefits of its knowledge-based simulator as well as industrial data.
Indeed, the status of an industrial chemical process is accessible through operating parameters and available monitoring measures.
However, the measures being inherently associated with uncertainty, it is necessary to make the data consistent with process knowledge.
Therefore, the goal is to find the best data set of operational parameters (input of the knowledge-based simulator) to provide the model to estimate the real process state known through monitoring measures (output of the knowledge-based simulator).
A convolutional neural network (CNN) is being developed in another postdoctoral project to solve the inverse problem to find the best input thanks to the measured output.
A consistent set of operating parameters is going to be obtained and state of the process is going to be known during the dynamic regime of the liquid- liquid extraction process.
To build the CNN, data will be obtained from the knowledge-based model and from measuring instruments.
As said above, the simulated data will be considered exact.
The goal of this postdoctoral project is to take into account the uncertainty of the measured data into account during the learning step of the CNN.
This first step is to evaluate the impact of the uncertainty of operational parameters on the outputs of the knowledge-based model.
This step will need to connect the knowledge-based model to URANIE, internal platform developed by CEA ISAS. Uranie is a plateform based on the ROOT data analysis software, developed by CERN.
URANIE notably displays algorithms allowing the propagation of uncertainties and sensitivity analyzes.
The results obtained with propagation of uncertainties technics will be compared with the measures of the output data and their own uncertainties.
This knowledge must be taken into account in the second part of the project.
The uncertainty observed on the outputs should be taken into account in the learning loop to improve the estimation of the operational parameters by the CNN.
The impact of these uncertainties on the CNN computed results must be assesed in order to trust the ability of the CNN to estimate the state of the process.
Through this project, we are at the heart of the thematic of digital simulation for the best control of complex systems.
This post-doc is an opportunity to build a tool to help the operation of a complex process by using the expertise of the process and modern techniques of artificial intelligence, which will be able to take into account the volume and “real time” requirements.
Qualifications
1. PhD in machine learning from an accredited university
2. Excellent communication skills, both verbal and written in English
3. Skills in Python language
4. Communication skills in French
5. Experience in uncertainty estimation
6. Experience in physics application is a plus
Salary & benefits
The salary will depend on the applicant’s profile and experience. The position comes with various social benefits (e.g. health insurance).
This position is open for one year.
Application and contacts
To apply send an updated CV and a motivation letter to:
Amandine DUTERME ([email protected])
Fabrice GAUDIER ([email protected])
Laurence CORNEZ ([email protected])
The position is open immediately (November 2021).
Review of applications will begin as soon as applications are received and continue until the position is filled or the deadline of January 1st 2022 is reached.