Advanced Block IV
An Introduction to the Topic of Continual Learning for AI
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.
In this workshop, you'll be able to learn about cutting-edge research efforts to address these issues and support the vision of truly adaptive, pervasive and scalable AI systems. In particular, we will introduce efficient continual learning strategies that can learn on-the-fly on newly available input data without accessing anymore data encountered previously.
After a brief introduction to the topic, we will play with the MNIST datasets in a continual object recognition scenario. At the end of the workshop you'd be able to acquire the basic knowledge and skills to make your own AI systems more scalable and adaptive.
About the lecturer:
Vincenzo Lomonaco is the Co-Founder of AI for People and President of ContinualAI.
Currently he is a Postdoctoral Researcher at the University of Bologna, Italy
Interested in: open science and ethical AI developments, neuroscience-grounded AI, continual/lifelong learning with deep architectures
For more than 3 years he has been working as a teaching assistant for Machine Learning and Computer Architectures courses