One motivation for representation learning is that learning algorithms can design features better and faster than humans can. To this end, we hold this challenge that does not explicitly require that entries use representation learning. Rather, introduce an entirely new dataset and invite students to solve it. The dataset for this challenge is a facial expression classification dataset that we have assembled from the internet.

This task is very easy for humans to do, for computers, not so much…

In this project you will try and design an intelligent algorithm for the task of distinguishing between 7 expressions (Angry, Disgust, Fear, Happy, Sad, Surprise, Neutral ). The training Data set is ~35000 face images and the test set is ~5000 image.

In this project we will develop and implement an application.

1. Supervisor:
   Elad Osherov
   04-8295741
   Email: eladosherov@yahoo.com
   
2. Field:
   Computer Vision
3. Requirements:
   046195 Intro to machine learning or an equivalent course
   046746 Computer vision algorithms and applications or an equivalent course
   Or a good knowledge in these topics
   
4. Project status:
   Taken by the student Elad Shashoua
   
5. Visit:
   Project web site