Neural Network Learning as an Inverse Problem
From MaRDI portal
Recommendations
Cited in
(20)- OCReP: an optimally conditioned regularization for pseudoinversion based neural training
- Regularization networks for inverse problems: A state-space approach
- Neural networks for linear inverse problems with incomplete data especially in applications to signal and image reconstruction
- Fixed-point algorithms for inverse of residual rectifier neural networks
- Manifold regularization based on Nyström type subsampling
- Regularization theory in the study of generalization ability of a biological neural network model
- Distributed semi-supervised support vector machines
- An unfeasibility view of neural network learning
- Learning from examples as an inverse problem
- Regularization algorithms for learning that are equivalent to multilayer networks
- Regularization techniques and suboptimal solutions to optimization problems in learning from data
- Solving inverse bimodular problems via artificial neural network
- Learning the pseudoinverse solution to network weights
- Neural nets learning as an inverse problem
- On the generalization problem
- Neural learning methods yielding functional invariance
- Sign stochastic gradient descents without bounded gradient assumption for the finite sum minimization
- Relaxation approach for learning neural network regularizers for a class of identification problems
- A neural network algorithm to pattern recognition in inverse problems
- Application of adjoint operators to neural learning
This page was built for publication: Neural Network Learning as an Inverse Problem
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5716212)
