Here you can find source code and data (corpora, ...) from my publications.

A Github repository is summarising all information on corpora with regular updates:

The current implementation of ESN/Reservoir that I use is available on this github repo:

Direct download of the Frontiers in NeuroRobotics 2014 paper is available here:

with the corresponding github page:

Please do not hesitate to contact me for more information on the corpora and source codes.

The Python implementation of our PLoS ONE (2013) paper needs MPD and Oger librairies:

- Modular toolkit for Processing Data (MPD): use Python 2.x version (not Python 3)

- OrGanic Environment for Reservoir computing (Oger) toolbox

Source code of Syntactic Reservoir Model (PLoS ONE, 2013) - This is the source code (Python) given in supplementary material of our PLoS ONE paper of 2013. It enables to reproduce experiments of the paper and gives a full access to the model: you will be able to modify all the parameters and change the model. It uses Python libraries like Numpy, and also uses the Oger toolbox developed within the EU FP7 Organic (2009-2013) project.

Read-Me for Source code of Syntactic Reservoir Model (PLoS ONE, 2013) - Read-me file explaining how to install and use the Python code of Syntactic Reservoir Model, given in supplementary material of PLoS ONE 2013 paper. - Videos used in the user experiment published in Hinaut et al. (2014) Frontiers in Neurorobotics. Theses videos were also used for the Hinaut et al. (2015) Cognitive Computation NIPS workshop paper.

Corpus 462 (PLoS ONE, 2013) - Corpus constituted of 462 pairings (grammatical constructions, "role-SW-mappings" (i.e. thematic roles for each semantic word)). This corpus was generated in order to have all the possible ordering of semantic words in a sentence (6 at max). Each construction could have 0 or 1 relative clause. This corpus was published in my PLoS ONE 2013 paper. It was also used in my ICANN 2012 and ICANN 2014 papers.