Self-Supervised learning for Neural Architecture Search (NAS)

The topic of this internship is related to Self-Supervised Learning, with the main idea of finding innovative methods to train a neural network in order to make a step forward in this field. A major problem that constrains our research is the use of the smallest possible amount of annotated data to obtain good final results. The aim is to enable new AIs to understand their environment and task more efficiently and with the least amount of data possible, so that they become accessible to companies that do not have the billions of data available to Google for example. The objective of this internship is to propose an innovative method that uses unlabelled data, i.e. data that will allow the AI to automatically learn to predict the correct outcome. To reach this stage, the steps to be followed can be defined as follows: (1) consult the state of the art and position ourself against it, (2) come up with ideas for development paths, (3) implement these ideas, (4) and finally test them to position ourself against the state of the art, and then start the sequence again.