One of the best Neural Networks/ Deep Learning tutorials can be found here. It is written by Andrew Ng, or as I think of him the best Machine Learning Sensei.
I have been doing the tutorial recently and will be giving hints as I go. So far I am upto the Convolutional Neural Network part (as of Sep 21).
The code is available in my github repository: https://github.com/sachinruk/Standford_DL
- When doing the 1st Deep Neural Network exercise (
supervised_dnn_cost.m) remember that error component is calculated for each individual example seperately. When calculating the gradient for we use . The transpose is important.
This blog post will be edited in the coming days. #comments powered by Disqus