Lower Bounds on the Complexity of Approximating Continuous Functions by Sigmoidal Neural Networks.
Michael SchmittPublished in: NIPS (1999)
Keyphrases
- continuous functions
- activation function
- neural network
- lower bound
- upper bound
- vc dimension
- real valued
- back propagation
- pattern recognition
- artificial neural networks
- objective function
- hidden layer
- feed forward
- differential equations
- expert systems
- genetic algorithm
- network architecture
- document retrieval
- learning rate
- bp neural network
- neural network model
- radial basis function
- fuzzy logic
- probabilistic model
- machine learning