#include <optimize.h>
Inheritance diagram for _gd_momentum:


Public Member Functions | |
| _gd_momentum (LM *lm, const Step &lr, const Step &m) | |
| const Dir & | direction () | 
| Search direction at w.   | |
Public Attributes | |
| Step | momentum | 
With momentum, the weight change is accumulated:
When the derivative is roughly constant, this speeds up the training by using an effectively larger learning rate
When the derivative somehow ``fluctuates'', the momentum stablizes the optimization to some exent by effectively decreasing the learning rate.
Definition at line 169 of file optimize.h.
      
  | 
  ||||||||||||||||
| 
 
 Definition at line 172 of file optimize.h.  | 
  
      
  | 
  
| 
 Search direction at w. 
 Reimplemented from _gradient_descent. Definition at line 175 of file optimize.h.  | 
  
      
  | 
  
| 
 
 Definition at line 170 of file optimize.h.  | 
  
 1.4.6