data_mining:neural_network:debugging

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
data_mining:neural_network:debugging [2017/08/20 00:11] – phreazerdata_mining:neural_network:debugging [2017/08/20 00:12] (current) – phreazer
Line 19: Line 19:
 For each i: For each i:
  
-$d\Theta_approx[i] = (J(\dots, \Theta_i+\epsilon,\dots) - J(\dots, \Theta_i-\epsilon,\dots)) / 2\epsilon$+$d\Theta_{approx}[i] = \frac{J(\dots, \Theta_i+\epsilon,\dots) - J(\dots, \Theta_i-\epsilon,\dots)}{2\epsilon}$ 
 + 
 +$\epsilon = 10^{-7}$
  • data_mining/neural_network/debugging.1503180669.txt.gz
  • Last modified: 2017/08/20 00:11
  • by phreazer