9/29/2017

realize parallel computing in MATLAB

Today, I realized parallel computing in MATLAB.

Summary:

I checked that Your laptop is 4 core CPU. So theoretically, it will save 3/4 time overall.

I ran 40 times to get the results for Vp and Vs prediction:

Average values: 0.8555 and 0.8295 in terms of R2; 0.0652 and 0.0684 in terms of NRMSE

Best Values: 0.8722 and 0.8492 in terms of R2 and; 0.0599 and 0.0603 in terms of NRMSE

Running time now is 348 seconds (about 900 seconds initially).

Next week, I will finish other tasks discussed today.

8 comments:

  1. Always record the computation time for this work..

    ReplyDelete
  2. I ran 40 times to get the results for Vp and Vs prediction:/.. what do you mean by run?? you will have to specify and record what youa re doing??

    are you initializing weights and bias different for each run..

    are you using different test and training set for each case?

    ReplyDelete
    Replies
    1. Yes, they are all different every time I train and test the ANN model.

      Delete
  3. I ran 40 times to get the results for Vp and Vs prediction:/.. what do you mean by run?? you will have to specify and record what youa re doing??

    are you initializing weights and bias different for each run..

    are you using different test and training set for each case?

    ReplyDelete
  4. do you see global minima? how much are you able to improve..

    ReplyDelete
    Replies
    1. I can just see the best local minima. It is about 2% more accurate than the average performance.

      Delete
  5. Replies
    1. I checked the laptop and it is a 4-core CPU. So I set 40 times to see if this method works. We can set it to 100 later when we start to write the paper.

      Delete