A Topological Framework for Deep Learning

Abstract

We utilize classical facts from topology to show that the classification problem in machine learning is always solvable under very mild conditions. Furthermore, we show that a softmax classification network acts on an input topological space by a finite sequence of topological moves to achieve the classification task. Moreover, given a training dataset, we show how topological formalism can be used to suggest the appropriate architectural choices for neural networks designed to be trained as classifiers on the data. Finally, we show how the architecture of a neural network cannot be chosen independently from the shape of the underlying data. To demonstrate these results, we provide example datasets and show how they are acted upon by neural nets from this topological perspective.

References in corpus (8)

• Understanding Neural Networks Through Deep Visualization
• The Loss Surfaces of Multilayer Networks
• Approximating Continuous Functions by ReLU Nets of Minimal Width
• A Topology Layer for Machine Learning
• Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions
• Autoencoding topology
• Topology of deep neural networks
• TopoAct: Visually Exploring the Shape of Activations in Deep Learning

Cited by in corpus (1)

• Topological Deep Learning: Classification Neural Networks