Implementing MaxMin Convolution Neural Networks- Better Accuracy Than Normal CNN

Implementing MaxMin Convolution Neural Networks- Better Accuracy Than Normal CNN(github.com)

23 points by ironislands 9 years ago | 5 comments

dontreact 9 years ago |

AllConv networks perform better and are an even simpler modification of the typical CNN architecture: just replace max pool layers with strides convolution. Why did the authors not benchmark against state of the art (also see fractional max pooling)

https://arxiv.org/abs/1412.6806

ironislands 9 years ago | |

Thanks for pointing me to this reference. I have implemented the baseline model mentioned in this paper. A sharp rise of 4% in classification accuracy is clearly observable. While there would be an improvement due to theoretical reasons, the difference between improved accuracy and original accuracy might get less on introducing other factors. It is on my TODO to add new results on different models and by introducing other things in a simple CNN as well.

ironislands 9 years ago |

This repository is for deep learning enthusiasts of all levels - a simple modification in classical CNN architecture to boost the accuracy. Based on a recently published paper. Even absolute beginners can understand what's written in there. Discussions are highly encouraged !

grogenaut 9 years ago |

Am I the only one who read that as better accuracy than Cable News Network?

ironislands 9 years ago | |

ROFL hahaha