A Topological Framework for Deep Learning
This work provides a foundational framework for understanding and designing neural networks from a topological perspective, potentially impacting all of ML/AI.
The paper tackles the classification problem in machine learning by applying topological principles to prove solvability under mild conditions and guide neural network architecture design based on data shape, with demonstrations on example datasets.
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.