Saturday, 6 April 2019

Model averaging

It is an ensemble methods use multiple models to obtain better predictive result than could be obtained from any of the constituent model alone.

It can be achieved by:
- Develop n models and train them with same train dataset.
- Evaluate n trained models with test dataset.
- Average n evaluated values with formula:
         y_pred = (y_pred_1 + y_pred_2 + y_pred_3 + y_pred_n ) / n
         y_pred_n is predected value of nth model on test dataset.

3 comments:

  1. This comment has been removed by the author.

    ReplyDelete
  2. Hello!
    How can I continuously upload the files in my sd card/spiffs to the external server as they come in? Also, how can I upload multiple files with the same extension (i.e. jpg) at once? http://www.iotsharing.com/2018/01/esp32-multipart-upload-file-and-download-via-http.html
    Thanks!

    ReplyDelete
  3. Hi friend,

    You have to modify the library since it only support one upload session.

    ReplyDelete