Developments over the last decade in big data tools, such as deep learning, have made their use widespread to the point where they occupy a large part of the data processing space. However, these methods are based on the availability of a large amount of reliable and unbiased data, but what happens when we have little data and many fields?

In this talk, we will discuss how in some fields such as AI and robotics it is possible to learn with little data. Methods such as reinforcement learning, dimensionality reduction and data representations that do not discard information are key to obtaining good models.

The session will be moderated by the AI Program Coordinator at CVC, Meritxell Bassolas, and the speaker will be postdoctoral researcher Adrià Colomé Figueras.

Objectiu de l'acte

• Learning and fitting regression models with little data
• Reinforcement learning
• Dimensionality reduction in data

T'interessa si ets...