Gradient Descent Finds Global Minima of Deep Neural Networks.
Simon S. DuJason D. LeeHaochuan LiLiwei WangXiyu ZhaiPublished in: ICML (2019)
Keyphrases
- global minima
- neural network
- global minimum
- cost function
- learning rules
- pattern recognition
- artificial neural networks
- loss function
- energy minimization
- genetic algorithm
- back propagation
- feed forward
- training algorithm
- error function
- neural network model
- neural nets
- training process
- multi layer
- objective function
- self organizing maps
- energy function
- recurrent neural networks
- global optimum
- search algorithm