The Break-Even Point on Optimization Trajectories of Deep Neural Networks.
Stanislaw JastrzebskiMaciej SzymczakStanislav FortDevansh ArpitJacek TaborKyunghyun ChoKrzysztof J. GerasPublished in: ICLR (2020)
Keyphrases
- neural network
- pattern recognition
- optimization algorithm
- highly non linear
- global optimization
- optimization method
- back propagation
- recurrent neural networks
- optimization problems
- moving objects
- optimization model
- fuzzy logic
- search algorithm
- support vector
- decision trees
- multilayer perceptron
- computer vision
- optimization methods
- training process
- activation function
- sample points
- discrete optimization
- genetic algorithm