Tutorial Page "Multi-Layer Neural Network"

amaas / stanford_dl_ex

Programming exercises for the Stanford Unsupervised Feature Learning and Deep Learning Tutorial

http://ufldl.stanford.edu/tutorial

MIT License

2.58k stars 1.6k forks source link

Tutorial Page "Multi-Layer Neural Network" #15

Open sunshineatnoon opened 9 years ago

sunshineatnoon commented 9 years ago

I think there is a problem in the formulation to compute the derivative of W and b in this tutorial. Isn't the W of layer l comes from error in layer l and activation in layer l-1? But the formulation suggests W in layer l comes from error in layer l+1 and activation in layer l. 2015-05-25 8 46 10 I think the right one should look like this 2015-05-25 8 29 50 The same goes to b. Or maybe I just misunderstood this, if so, please point out, thanks!

iammarvelous commented 8 years ago

You are right. W(l) lies between delta(l) and a(l-1).