…dre Cadrin-Chenevert: It is fascinating to see how the fast.ai students are tightly bound together. We are like a big international family. The democratization of deep learning is an important social mission and we are all part of it.
More research would certainly improve this accuracy even more but the main point is that with its default settings, fastai v1 allows to approximate the level of the art in FER on the Kaggle’s Facial Expression Recognition 2013 Challenge.
My machine learning and deep learning journey almost ended before it ever began back in early January of this year, when I saw the following page on scikit-learn.org. I momentarily and incorrectly assumed I wasn’t “technical” enough to grasp machine learning because I couldn’t immediately understand the mathematical notation that was pasted into articles all over the website.