We are looking for an engineer for at least one year to work with the open source ReservoirPy library on health data.
You will be working in Bordeaux, France in the Mnemosyne computational neuroscience group
https://team.inria.fr/mnemosyne in collaboration with other Bordeaux teams involved in biostatistics and machine learning.
* ReservoirPy
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.
* Deadline: 20th of September 2022
For informal questions send an email to xavier dot hinaut at inria dot fr.
* Contract
Engineer contract of 1 year, with possibility to extend the contract to more years or to continue in the team as PhD student.
* Benefits package
- Subsidized meals
- Partial reimbursement of public transport costs
- Possibility of partial teleworking 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
[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.
https://hal.inria.fr/hal-02595026v2/document[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).
https://hal.inria.fr/hal-03761440/document[4] Jaeger, H., & Haas, H. (2004). Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. science, 304(5667), 78-80.
[5] Lukoševičius, M., & Jaeger, H. (2009). Reservoir computing approaches to recurrent neural network training. Computer Science Review, 3(3), 127-149.