In questo talk, esploremo insieme il concetto di apprendimento automatico continuo, le sue motivazioni fondanti e perché esso rappresenta una tecnologia abilitante per lo sviluppo di un’Intelligenza Artificiale efficiente, scalabile e sostenibile.
Abstract completo in inglese:
Humans have the extraordinary ability to learn continually from experience. Not only we can apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning, constantly and efficiently updating our biased understanding of the external world.
On the contrary, current AI systems are usually trained offline on huge datasets and later deployed with frozen learning capabilities as they have been shown to suffer from catastrophic forgetting if trained continuously on changing data distributions.
A common, practical solution to the problem is to re-train the underlying prediction model from scratch and re-deploy it as a new batch of data becomes available. However, this naive approach is incredibly wasteful in terms of memory and computation other than impossible to sustain over longer timescales and frequent updates.
In this talk, we will discuss recent advances on machines that can learn continually and their important relationships with the fields of Neuroscience and Robotics. Finally, we will discuss the broader impact of Continual Learning in the context of a more sustainable vision of Artificial Intelligence and its applications.
Nota: L’evento si terrà in italiano
Vincenzo Lomonaco è AI & Continual Learning Assistant Professor @ Unipi | Co-Founding President and Lab Director @ ContinualAI | Board Member @ AI for People | Co-Host @ Smarter Podcast.