On the Stability Properties and the Optimization Landscape of Training Problems with Squared Loss for Neural Networks and General Nonlinear Conic Approximation Schemes.
Constantin ChristofPublished in: CoRR (2020)
Keyphrases
- approximation schemes
- neural network
- stability analysis
- special case
- optimization problems
- training process
- highly non linear
- training algorithm
- combinatorial optimization
- approximation algorithms
- artificial neural networks
- sufficient conditions
- back propagation
- lyapunov function
- image analysis
- image processing
- computer vision
- genetic algorithm