Is it necessary to initialized the wieghts for retraining in matlab with nntool?

1 次查看（过去 30 天）
Daud
Daud 2012-9-7
i am doing a speech recognition problem; using nntool; i have found most of time that during the first attempt of training; the output is not good; so i have to retrain.
but my queries is: should i need to reinitialized the weights for retrain.
What if i don't re-initialized and train again?; actually i found better result without re-initializing.
i want to know which approach is right and why?
  1 个评论
Greg Heath
Greg Heath 2012-9-9
The short answer is I typically make several runs (~ 10) with random weight intialization for each setting of other parameters (e.g., No. of hidden nodes). Poor results caused by converging to a high local miimum are best cured by reinitialization.

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Greg Heath
Greg Heath 2012-9-7
Some creation functions like newff, newfit, newpr, fitnet, patternnet and feedforwardnet are self initializing with random weights.
It is not clear if you are becoming successful by starting again with a new set of random weights or are just increasing the number epochs.
More information is needed.
  3 个评论
显示 1更早的评论
Greg Heath
Greg Heath 2012-9-9
Several caveats
1. I am not familiar with nntool so any advice I give re that should be accepted with a grain of salt. If you switch to the command line mode you can have more confidence in my advice.
2. Many of my answers are made w.r.t. my years of practical experience in NN design and, in retirement, my 8 years experience with obsoleted MATLAB functions like newff, newfit and newpr.
3. I have recently learned that several subtle changes have been made w.r.t. current replacements of the new**s : feedforwardnet, fitnet and patternnet.
4. In particular, the newer functions do not automatically initialize weights upon creation. Weights are either initialized via configure or via train. I have not been successfull in decifering the new source code.
5. Currently I don't have the time to make the few revealing numerical experiments.
6. So, right now, I am not sure what exactly happens when train is called after configure or when train is run in multiple steps.
7. I suggest you printout the weights before and after calls to configure and 1 epoch of train. ...shouldn't take much time.
8. The next step is find out exactly what the function revert does when thrown into the mix.
Hope this helps.
Greg

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by