Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent
- Resource Type
- Working Paper
- Authors
- Kohler, Michael; Krzyzak, Adam; Walter, Benjamin
- Source
- Subject
- Statistics - Machine Learning
Computer Science - Machine Learning
- Language
Image classification based on over-parametrized convolutional neural networks with a global average-pooling layer is considered. The weights of the network are learned by gradient descent. A bound on the rate of convergence of the difference between the misclassification risk of the newly introduced convolutional neural network estimate and the minimal possible value is derived.