DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound Propagation.
Haitham KhedrYasser ShoukryPublished in: CoRR (2023)
Keyphrases
- neural network
- worst case
- upper bound
- vapnik chervonenkis dimension
- artificial neural networks
- computational complexity
- pattern recognition
- fuzzy logic
- lower bound
- polynomial hierarchy
- back propagation
- complexity bounds
- recurrent neural networks
- polynomial size
- error bounds
- rule extraction
- space complexity
- network architecture
- training process
- neural nets
- feed forward
- neural network model
- decision problems
- genetic algorithm
- machine learning