Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes.
Kenji KawaguchiJiaoyang HuangPublished in: Allerton (2019)
Keyphrases
- neural network
- global minima
- global minimum
- cost function
- real world
- pattern recognition
- neural network model
- learning rules
- objective function
- artificial neural networks
- fuzzy logic
- loss function
- self organizing maps
- multiscale
- higher order
- back propagation
- global optimization
- multi layer
- computer vision
- genetic algorithm