Question: When a learning algorithm changes a network s parameters to improve performance ( i . e . , reduce error ) , it can sometimes
When a learning algorithm changes a networks parameters to improve performance ie reduce error it can sometimes find itself in a region of state space where the error surface does not allow any further reduction in error, even though performance is still far from perfect. This is called:
Step by Step Solution
There are 3 Steps involved in it
1 Expert Approved Answer
Step: 1 Unlock
Question Has Been Solved by an Expert!
Get step-by-step solutions from verified subject matter experts
Step: 2 Unlock
Step: 3 Unlock
