Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent.
Michael KohlerAdam KrzyzakBenjamin WalterPublished in: CoRR (2024)
Keyphrases
- image analysis
- convolutional neural network
- image features
- single image
- image classification
- multiscale
- image content
- image data
- support vector machine
- input image
- edge detection
- convergence rate
- test images
- image representation
- feature points
- high resolution
- feature selection
- scale space
- machine learning
- feature space
- training data
- region of interest
- image segmentation
- image collections