My batch gradient descent algorithm is not converging (i.e., the cost function does not decrease with every iteration, even though I have set my learning rate quiet small and have verified with different learning rates, both large and even smaller). What could be possibly be going wrong?
-
-
Answer:
The most likely answer is a bug in your implementation. :) Your learning rate may not actually be as small as you think, or not small enough for this data set. You may have a normalization problem, where your data is "small" relative to learning rate only along a few dimensions.
Sean Owen at Quora Visit the source
Related Q & A:
- Can allergies cause dizziness, even though I am not stuffy?Best solution by Yahoo! Answers
- Why can't I access my Yahoo mail even though I can log into Yahoo?Best solution by Yahoo! Answers
- Why do I pee a little when I sneeze, even though I'm not pregnant?Best solution by answers.yahoo.com
- What to wear to a pool party even though I am not swimming?Best solution by corporette.com
- Can i celebrate kwanza even though i white?Best solution by Yahoo! Answers
Just Added Q & A:
- How many active mobile subscribers are there in China?Best solution by Quora
- How to find the right vacation?Best solution by bookit.com
- How To Make Your Own Primer?Best solution by thekrazycouponlady.com
- How do you get the domain & range?Best solution by ChaCha
- How do you open pop up blockers?Best solution by Yahoo! Answers
For every problem there is a solution! Proved by Solucija.
-
Got an issue and looking for advice?
-
Ask Solucija to search every corner of the Web for help.
-
Get workable solutions and helpful tips in a moment.
Just ask Solucija about an issue you face and immediately get a list of ready solutions, answers and tips from other Internet users. We always provide the most suitable and complete answer to your question at the top, along with a few good alternatives below.