no code implementations • NeurIPS Workshop ICBINB 2021 • Amélie Chatelain, Amine Djeghri, Daniel Hesslow, Julien Launay, Iacopo Poli
Recent work has identified simple empirical scaling laws for language models, linking compute budget, dataset size, model size, and autoregressive modeling loss.
no code implementations • 20 Feb 2020 • Ahmed Rachid Hazourli, Amine Djeghri, Hanan Salam, Alice Othmani
Results show that the proposed approach achieves state-of-art FER deep learning approaches performance when the model is trained and tested on images from the same dataset.