AI & computational neuroscience researcher · interpretable ML and reproducible analysis for complex biomedical and behavioral data.
Portfolio · ORCID · Google Scholar · LinkedIn
I work at the intersection of machine learning, computational neuroscience, and epidemiology. My research combines interpretable models with auditable workflows to study cognition, brain health, and behavior.
Current interests include interpretable deep learning, survival analysis, multimodal biomedical data, and reproducible research. I am based in Paris and open to research collaborations and applied AI projects.
-
share-childhood-dementia — Reproducible Python/R workflow for studying childhood risk factors and incident dementia in SHARE, with participant-grouped machine learning, multiple imputation, survival models, population-attributable fractions, and synthetic test data.
-
sparsity_beauty — Research code accompanying a PLOS Computational Biology study of how neural activation sparsity in deep networks relates to human aesthetic judgments.
-
hallucinations — Dated public snapshot of the analysis protocol and prospective falsification criteria for a predictive-coding study of hallucinations. The development repository remains private.
-
website_dibot — Source code for my research and applied-AI portfolio.
-
Nicolas M. Dibot, Julien P. Renoult, & William Puech (2025). “Generation and Editing of Mandrill Faces: Application to Sex Editing and Assessment.” ACM Transactions on Multimedia Computing, Communications, and Applications, 21(8), 1–23. DOI: 10.1145/3744249
-
Nicolas M. Dibot, Sonia Tieo, Tamra C. Mendelson, William Puech, & Julien P. Renoult (2023). “Sparsity in an Artificial Neural Network Predicts Beauty: Towards a Model of Processing-Based Aesthetics.” PLOS Computational Biology, 19(12), e1011703. DOI: 10.1371/journal.pcbi.1011703 · Code
-
Sonia Tieo, Melvin Bardin, Roland Bertin-Johannet, Nicolas Dibot, Tamra C. Mendelson, William Puech, & Julien P. Renoult (2025). “Comparing Activation Typicality and Sparsity in a Deep CNN to Predict Facial Beauty.” Computational Brain & Behavior, 8, 249–261. DOI: 10.1007/s42113-024-00231-7
Figure 1 from Dibot et al. (2023), Sparsity in an artificial neural network predicts beauty, PLOS Computational Biology. © 2023 Dibot et al., CC BY 4.0. Reproduced without modification.
For research collaborations, scientific consulting, or applied AI work, see my portfolio or contact me via LinkedIn.