MOOC on topology and neural networks

In this masterclass, Asier Gutiérrez, researcher in the Life Sciences department of the BSC-CNS, will invite the public to learn about the latest advances in Algebraic Topology applied to Neural Networks.

A wide audience, will not go into complex mathematical principles, technicalities or references to articles that might be difficult to understand. Thus, it will focus on explaining the latest developments in the referred areas and the range of possibilities from a practical standpoint, which will be accessible to all attendees.

ADDRESSED TO:

1. Professionals working in the field of Artificial Intelligence (more specifically in Deep Learning) who want to learn about tools to be used on a daily basis.
2. Artificial Intelligence researchers who want to deepen their understanding of how Deep Learning networks learn.
3. General public, journalists and scientific disseminators interested in key developments in Deep Learning.

PROGRAMME:

Part 1: Brief introduction to Persistent Homology. Part 2: Neural Network Modeling. Part 3: Comparability of architectures. Part 4: Characterization of learning. Part 5: Current challenges of Persistent Homology and its application to Neural Networks. Part 6: Use cases of Persistent Homology. Part 7: Libraries.