Fiber Bundle Networks: A Geometric Machine Learning Paradigm
By: Dong Liu
Potential Business Impact:
Makes AI understand things by seeing patterns.
We propose Fiber Bundle Networks (FiberNet), a novel machine learning framework integrating differential geometry with machine learning. Unlike traditional deep neural networks relying on black-box function fitting, we reformulate classification as interpretable geometric optimization on fiber bundles, where categories form the base space and wavelet-transformed features lie in the fibers above each category. We introduce two innovations: (1) learnable Riemannian metrics identifying important frequency feature components, (2) variational prototype optimization through energy function minimization. Classification is performed via Voronoi tessellation under the learned Riemannian metric, where each prototype defines a decision region and test samples are assigned to the nearest prototype, providing clear geometric interpretability. This work demonstrates that the integration of fiber bundle with machine learning provides interpretability and efficiency, which are difficult to obtain simultaneously in conventional deep learning.
Similar Papers
Emergent Riemannian geometry over learning discrete computations on continuous manifolds
Machine Learning (CS)
Helps computers learn to make decisions from pictures.
Walking on the Fiber: A Simple Geometric Approximation for Bayesian Neural Networks
Machine Learning (CS)
Lets computers learn with less guessing.
Neural Feature Geometry Evolves as Discrete Ricci Flow
Machine Learning (CS)
Helps computers learn better by understanding shapes.