@inproceedings{fdi:010087182,
  title = {{C}hecklist strategies to improve the reproducibility of {D}eep {L}earning experiments with an illustration [poster]},
  author = {{B}en {A}bbes, {A}. and {M}achicao, {J}. and {M}eneguzzi, {L}. and {C}orr{\^e}a, {P}.{L}.{P}. and {S}pecht, {A}. and {D}avid, {R}. and {S}ubsol, {G}. and {V}ellenich, {D}.{F}. and {D}evillers, {R}odolphe and {S}tall, {S}. and {M}ouquet, {N}. and {C}haumont, {L}. and {B}erti-{E}quille, {L}aure and {M}ouillot, {D}.},
  editor = {},
  language = {{ENG}},
  abstract = {{T}he challenges of {R}eproducibility and {R}eplicability ({R}&{R}) have become a focus of attention in order to promote open and accessible research. {T}herefore,  efforts have been made to develop good practices for {R}&{R} in the area of computer science. {N}evertheless,  {D}eep {L}earning ({DL}) based experiments remain difficult to reproduce by others due to the complexity of these techniques. {I}n addition, several challenges concern the use of massive and heterogeneous data that contribute to the complexity of this {R}&{R}. {F}irstly, we compiled three different aspects to help researchers to improve {R}&{R}. {T}his compilation was based on machine learning checklists, guidelines, and principles from {FAIR}. {T}herefore, this compilation is useful for a (1) researcher seeking to reproduce a paper, (2) an author reporting on an experiment, and (3) a reviewer seeking to qualify the scientific contributions of the work. {S}econdly, we illustrate the compilation of three recent {DL} experiments for socio-economic estimation using remotely sensed data.},
  keywords = {},
  numero = {},
  pages = {1  multigr.},
  booktitle = {},
  year = {2022},
  DOI = {10.5281/zenodo.6587702},
  URL = {https://www.documentation.ird.fr/hor/fdi:010087182},
}