Facial Expression Recognition

Working with the FER2013[1] dataset, the goal of this assignment was to empirically see and understand the impact of different architectures and hyper-parameters on prediction over the dataset.
The results are not groundbreaking(not so bad either) but indeed showing the importance of choosing the right parameters.
This assignment was given as part of the course "Deep Learning"(Fall 2022) by Prof. Giuseppe Serra and othe fellows from "AI Lab Udine": http://ailab.uniud.it.




[1]"Challenges in Representation Learning: A report on three machine learning contests." I Goodfellow, D Erhan, PL Carrier, A Courville, M Mirza, B Hamner, W Cukierski, Y Tang, DH Lee, Y Zhou, C Ramaiah, F Feng, R Li, X Wang, D Athanasakis, J Shawe-Taylor, M Milakov, J Park, R Ionescu, M Popescu, C Grozea, J Bergstra, J Xie, L Romaszko, B Xu, Z Chuang, and Y. Bengio. arXiv 2013.