Analysis of convolutional neural network image classifiers in a rotationally symmetric model

05/11/2022
by   Michael Kohler, et al.
11

Convolutional neural network image classifiers are defined and the rate of convergence of the misclassification risk of the estimates towards the optimal misclassification risk is analyzed. Here we consider images as random variables with values in some functional space, where we only observe discrete samples as function values on some finite grid. Under suitable structural and smoothness assumptions on the functional a posteriori probability, which includes some kind of symmetry against rotation of subparts of the input image, it is shown that least squares plug-in classifiers based on convolutional neural networks are able to circumvent the curse of dimensionality in binary image classification if we neglect a resolution-dependent error term. The finite sample size behavior of the classifier is analyzed by applying it to simulated and real data.

READ FULL TEXT

page 8

page 17

page 19

research
03/03/2020

On the rate of convergence of image classifiers based on convolutional neural networks

Image classifiers based on convolutional neural networks are defined, an...
research
05/31/2021

Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling

Image classification is considered, and a hierarchical max-pooling model...
research
11/29/2021

On the rate of convergence of a classifier based on a Transformer encoder

Pattern recognition based on a high-dimensional predictor is considered....
research
11/27/2020

Statistical theory for image classification using deep convolutional neural networks with cross-entropy loss

Convolutional neural networks learned by minimizing the cross-entropy lo...
research
06/05/2022

A statistical analysis of an image classification problem

The availability of massive image databases resulted in the development ...
research
09/04/2015

A nonlinear aggregation type classifier

We introduce a nonlinear aggregation type classifier for functional data...
research
09/26/2017

Learning to Label Affordances from Simulated and Real Data

An autonomous robot should be able to evaluate the affordances that are ...

Please sign up or login with your details

Forgot password? Click here to reset