Topological Deep Learning

Nour FahmyTotal time needed: ~20 minutes
Learning Objectives
Introduction to topological deep learning, and more specifically topological convolutional neural networks.
Potential Use Cases
TCNNs learn faster, on less data, with fewer learned parameters, and with greater generalizability and interpretability than conventional CNNs.
Target Audience
INTERMEDIATEML practitioners and enthusiasts who are interested in developments of TDA
Go through the following annotated items in order:
OTHER 1. Convolutional Neural Network
  • What is a convolutional neural network?
10 minutes
PAPER 2. Topological Approaches to Deep Learning
  • How can we use topology to understand the internal states of a CNN?
10 minutes
ARTICLE 3. Topological Deep Learning
  • How can we use the latent manifolds of image data in the structure of convolutional neural networks?
20 minutes

Concepts Convered