<html><head><meta http-equiv="content-type" content="text/html; charset=utf-8"></head><body style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;"><div>Please find below an offer for an intership from February/March to July/August 2024 in Mnemosyne team at Inria, Bordeaux, France</div><div><br></div><div># Title</div><div>ReservoirGPT</div><div>Large Language Model to help development with ReservoirPy</div><div><br></div><div># Keywords</div><div>Machine Learning, Large Language Model, Recurrent Neural Network (RNN), Reservoir Computing,</div><div><br></div><div># Supervisors</div><div>Xavier Hinaut, Researcher at Inria (Bordeaux, France)</div><div>xavier.hinaut@inria.fr</div><div><br></div><div># Research team & internship location</div><div>Mnémosyne Team: Inria Bordeaux Sud-Ouest, LABRI & Institut des Maladies Neurodégénératives (Centre Broca Aquitaine, Carreire campus)</div><div>https://team.inria.fr/mnemosyne</div><div><br></div><div># Introduction and scientific context</div><div>ReservoirPy is a library developed in the Mnemosyne Inria team in Bordeaux, France. ReservoirPy is a simple user-friendly library based on Python scientific modules. It provides a flexible interface to implement efficient Reservoir Computing (RC) architectures with a particular focus on Echo State Networks (ESN). Advanced features of ReservoirPy allow to improve computation time efficiency on a simple laptop compared to basic Python implementation, with datasets of any size.</div><div>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. Moreover, graphical tools are included to easily explore hyperparameters with the help of the hyperopt library. ReservoirPy is available on GitHub:</div><div>https://github.com/reservoirpy/reservoirpy</div><div>with the open source MIT license, it includes a detailed documentation https://reservoirpy.readthedocs.io</div><div>and a pypi package for easy installation.</div><div><br></div><div><br></div><div># Objectives</div><div>This six-month Master’s spring 2024 internship is centered on the ambitious goal of developing a cutting-edge Large Language Model (LLM) based service, specifically tailored to assist in programming with the ReservoirPy library. The primary objective is to create an AI-powered tool that simplifies and enhances the coding experience for users working with reservoir computing. This involves not only integrating the LLM with ReservoirPy to provide real-time coding assistance and error correction, but also customizing the model to understand and effectively respond to industry-specific terminologies and queries. Through this project, the intern will contribute to a pioneering effort in AI-assisted coding, bridging the gap between advanced AI language capabilities and practical, domain-specific programming needs.</div><div><br></div><div># Required skills</div><div>- Expertise in Python</div><div>- Knowledge in software project management</div><div><br></div><div>- Experience with ChatGPT and Large Language Model</div><div>- General knowledge in machine learning (training procedure, evaluation, metrics, visualizations, Python tools...) is a plus</div><div>- General knowledge about artificial neural networks</div><div><br></div><div># Applications</div><div>Deadline: as soon as possible; as soon as a good application is received it will be considered. Please contact Xavier Hinaut for any questions, and send your application (CV + cover letter) (Email at the top of the internship proposal).</div><div>References</div><div><br></div><div>[1] Trouvain, N., & Hinaut, X. (2022). reservoirpy: A Simple and Flexible Reservoir Computing Tool in Python.</div><div><br></div><div>[2] « ReservoirPy » https://github.com/reservoirpy/reservoirpy</div><div><br></div><div><br></div><div><br></div><br><br><div>
<meta charset="UTF-8"><div dir="auto" style="caret-color: rgb(0, 0, 0); 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;"><div>Xavier Hinaut<br>Inria Research Scientist<br>www.xavierhinaut.com -- +33 5 33 51 48 01<br>Mnemosyne team, Inria, Bordeaux, France -- https://team.inria.fr/mnemosyne<br>& LaBRI, Bordeaux University -- https://www4.labri.fr/en/formal-methods-and-models<br>& IMN (Neurodegeneratives Diseases Institute) -- http://www.imn-bordeaux.org/en<br>---<br>Our Reservoir Computing library: https://github.com/reservoirpy/reservoirpy</div></div>
</div>
<br></body></html>