A singular Riemannian geometry approach to Deep Neural Networks I. Theoretical foundations.
Alessandro BenfenatiAlessio MartaPublished in: Neural Networks (2023)
Keyphrases
- theoretical foundation
- neural network
- information geometry
- theoretical framework
- geodesic distance
- artificial neural networks
- pattern recognition
- riemannian manifolds
- shape analysis
- back propagation
- multi layer
- multilayer perceptron
- tangent space
- deep learning
- affine invariant
- euclidean space
- neural nets
- neural network model
- fault diagnosis
- three dimensional
- genetic algorithm
- recurrent neural networks
- geometric structure
- fuzzy logic
- reinforcement learning
- tensor field
- euclidean metric