Neural Networks based on Distance Measures
This repo provides an implementation of a neural network based on distance measures and Gaussian activation function. It should reproduce the results on permutation invariant MNIST reported in the paper:
Thomas Kurbiel, Shahrzad Khaleghian,
Training of Deep Neural Networks based on Distance Measures using RMSProp,
arXiv preprint arXiv:1708.01911 (2015)
available at https://arxiv.org/pdf/1708.01911.pdf
Please copy the two MATLAB helper functions "loadMNISTImages" and "loadMNISTLabels" for extracting the data. These functions are available at http://ufldl.stanford.edu/wiki/resources/mnistHelper.zip.
The MNIST dataset can be downloaded from http://yann.lecun.com/exdb/mnist/.
Source: http://ufldl.stanford.edu/wiki/index.php/Using_the_MNIST_Dataset