<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">Last days to apply for this engineer position on ReservoirPy:<div class=""><a href="https://jobs.inria.fr/public/classic/en/offres/2022-05343" class="">https://jobs.inria.fr/public/classic/en/offres/2022-05343</a></div><div class=""><br class=""></div><div class="">Best regards,</div><div class=""><br class=""></div><div class="">Xavier Hinaut</div><div class=""><div><br class=""><blockquote type="cite" class=""><div class="">Le 6 sept. 2022 à 12:18, Xavier Hinaut <<a href="mailto:xavier.hinaut@inria.fr" class="">xavier.hinaut@inria.fr</a>> a écrit :</div><br class="Apple-interchange-newline"><div class=""><meta http-equiv="Content-Type" content="text/html; charset=utf-8" class=""><div style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div class="">We are looking for an engineer for at least one year to work with the open source ReservoirPy library on health data.</div><div class="">You will be working in Bordeaux, France in the Mnemosyne computational neuroscience group <a href="https://team.inria.fr/mnemosyne" class="">https://team.inria.fr/mnemosyne</a> in collaboration with other Bordeaux teams involved in biostatistics and machine learning.</div><div class=""><br class=""></div><div class="">More info and online application: <a href="https://jobs.inria.fr/public/classic/en/offres" class="">https://jobs.inria.fr/public/classic/en/offres</a></div><div class=""><br class=""></div><div class="">* ReservoirPy</div><div class="">ReservoirPy [1, 2, 3] is a simple user-friendly library based on Python scientific modules. It provides a flexible interface to implement efficient Reservoir Computing (RC) [5] architectures with a particular focus on Echo State Networks (ESN) [4]. Advanced features of ReservoirPy allow to improve computation time efficiency on a simple laptop compared to basic Python implementation. Some of its features are: offline and online training, parallel implementation, sparse matrix computation, fast spectral initialization, advanced learning rules (e.g. Intrinsic Plasticity) etc. It also makes possible to easily create complex architectures with multiple reservoirs (e.g. deep reservoirs), readouts, and complex feedback loops. Moreover, graphical tools are included to easily explore hyperparameters with the help of the hyperopt library. It includes several tutorials exploring exotic architectures and examples of scientific papers reproduction.</div><div class=""><br class=""></div><div class="">Github: <a href="https://github.com/reservoirpy/reservoirpy" class="">https://github.com/reservoirpy/reservoirpy</a></div><div class="">Documentation: <a href="https://reservoirpy.readthedocs.io/" class="">https://reservoirpy.readthedocs.io</a></div><div class="">Related projects: <a href="https://github.com/reservoirpy" class="">https://github.com/reservoirpy</a></div><div class="">Twitter: <a href="https://twitter.com/reservoirpy" class="">https://twitter.com/reservoirpy</a></div><div class=""><br class=""></div><div class="">* Deadline: 20th of September 2022</div><div class="">For informal questions send an email to xavier dot hinaut at inria dot fr.</div><div class="">Online application: <a href="https://jobs.inria.fr/public/classic/en/offres" class="">https://jobs.inria.fr/public/classic/en/offres</a></div><div class=""><br class=""></div><div class="">* Contract</div><div class="">Engineer contract of 1 year, with possibility to extend the contract to more years or to continue in the team as PhD student.</div><div class=""><br class=""></div><div class="">* Benefits package</div><div class="">- Subsidized meals</div><div class="">- Partial reimbursement of public transport costs</div><div class="">- Possibility of partial teleworking and flexible organization of working hours</div><div class="">- Professional equipment available (videoconferencing, loan of computer equipment, etc.)</div><div class="">- Social, cultural and sports events and activities</div><div class="">- Access to vocational training</div><div class="">- Social security coverage</div><div class=""><br class=""></div><div class="">[1] Trouvain N, Pedrelli L, Dinh TT, Hinaut X (2020). Reservoirpy: an efficient and user-friendly library to design echo state networks. International Conference on Artificial Neural Networks, 494-505. <a href="https://hal.inria.fr/hal-02595026v2/document" class="">https://hal.inria.fr/hal-02595026v2/document</a></div><div class="">[2] Trouvain, N., Rougier, N. P., & Hinaut, X. (2022). Create Efficient and Complex Reservoir Computing Architectures with ReservoirPy. In FROM ANIMALS TO ANIMATS 16: The 16th International Conference on the Simulation of Adaptive Behavior (SAB2022). <a href="https://hal.inria.fr/hal-03761440/document" class="">https://hal.inria.fr/hal-03761440/document</a></div><div class="">[3] Nathan Trouvain, Xavier Hinaut. reservoirpy: A Simple and Flexible Reservoir Computing Tool in Python. 2022. HAL preprint hal-03699931. <a href="https://hal.inria.fr/hal-03699931/document" class="">https://hal.inria.fr/hal-03699931/document</a></div><div class="">[4] Jaeger, H., & Haas, H. (2004). Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. science, 304(5667), 78-80.</div><div class="">[5] Lukoševičius, M., & Jaeger, H. (2009). Reservoir computing approaches to recurrent neural network training. Computer Science Review, 3(3), 127-149.</div><br class=""><br class=""><div class="">
<meta charset="UTF-8" class=""><div dir="auto" style="caret-color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div class="">Xavier Hinaut<br class="">Inria Research Scientist<br class=""><a href="http://www.xavierhinaut.com/" class="">www.xavierhinaut.com</a> -- +33 5 33 51 48 01<br class="">Mnemosyne team, Inria, Bordeaux, France -- <a href="https://team.inria.fr/mnemosyne" class="">https://team.inria.fr/mnemosyne</a><br class="">& LaBRI, Bordeaux University -- <a href="https://www4.labri.fr/en/formal-methods-and-models" class="">https://www4.labri.fr/en/formal-methods-and-models</a><br class="">& IMN (Neurodegeneratives Diseases Institute) -- <a href="http://www.imn-bordeaux.org/en" class="">http://www.imn-bordeaux.org/en</a><br class="">---<br class="">Our Reservoir Computing library: <a href="https://github.com/reservoirpy/reservoirpy" class="">https://github.com/reservoirpy/reservoirpy</a></div></div>
</div>
<br class=""></div></div></blockquote></div><br class=""></div></body></html>