I’m a 2nd year PhD Student in computer science at Université de Montréal (UdeM) and Mila (Quebec Artificial Intelligence Institute); supervised by Guillaume Rabusseau and Guillaume Dumas.

I am interested in understanding generalization and optimization in deep learning, both from dynamical systems and neuroscience perspectives. My main interest is understanding what causes the triplet (model, optimization, data properties) to generalize beyond the training set, the causal relationship between complexity measures, initialization, hyperparameters and generalization, the functional metrics (progression measures) that differentiate a neuronal network before and after learning.

Before starting a PhD, I was a visiting student researcher at UdeM and a reseach intern at Mila. I worked under the supervision of professor Yoshua Bengio and his postdoctoral fellow Dianbo Liu on Biasly (detecting and mitigating racist and sexist discrimination in online texts).

I hold a master’s of engineering in computer science from the National Advanced School of Engineering Yaounde, Cameroon.

«Une theorie ne doit pas etre juger par le realisme de ses hypotheses, mais par la correction de ses predictions par rapport à son domaine cible»: Milton friedman.