A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction — mentioned by gambler

Thu, 09 Jan 2020 23:04:59 GMT

Can someone explain to me why advances in actual model performance come from using analogies from physics when there are papers that supposedly provide a mathematical explanation of convolution? "A Mathematical Theory of Deep ConvolutionalNeural Networks for Feature Extraction": https://arxiv.org/pdf/1512.06293.pdf "Understanding Convolutional Neural Networks with A Mathematical Model": https://arxiv.org/pdf/1609.04112.pdf

Paper and discussion history. A mention is not an endorsement.

A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction — HN submission

Fri, 01 Jan 2016 14:30:23 GMT

A Theory of Deep Convolutional Neural Networks for Feature Extraction

51 points; 5 discussion replies on HN. Paper and source history. A submission is not an endorsement.

A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction · HackerPapers discussions

A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction — mentioned by gambler

A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction — HN submission