Towards Lower Bounds on the Depth of ReLU Neural Networks.
Christoph HertrichAmitabh BasuMarco Di SummaMartin SkutellaPublished in: NeurIPS (2021)
Keyphrases
- lower bound
- neural network
- upper bound
- branch and bound algorithm
- branch and bound
- pattern recognition
- depth map
- objective function
- artificial neural networks
- back propagation
- multi layer
- depth information
- recurrent neural networks
- self organizing maps
- worst case
- fuzzy logic
- lower and upper bounds
- randomly generated problems
- sample size
- vc dimension
- multilayer perceptron
- np hard
- special case
- genetic algorithm
- neural nets
- expert systems
- training process
- activation function
- optimal solution
- rule extraction
- quadratic assignment problem
- machine learning