Prediction ability of a neural network

4 Ansichten (letzte 30 Tage)
Yiming
Yiming am 28 Nov. 2013
Kommentiert: Greg Heath am 30 Nov. 2013
Hi all,
recently I am doing some simulation and prediction work using neural networks. During the days, I have some theoretical questions regarding to NN. I appreciate it so much if anyone can help me solve them:
1. Is there any relationship between a neural network and a finite-state machine?
From my point of view, I always feel that the training of a neural network is just the process to teach the network to know its input-output relations. Sometimes, if you give a input u_i within the input range [u_min, u_max] but never occurs in the trained data, the reliability of the output is really poor.
2. How to make sure that the prediction of a neural network is reliable?
3. Somebody told me that, if a problem can be solved by traditional methods, never use neural networks. Therefore, I am wondering that, besides the high computation complexity, does neural networks have any other drawback or limitation?
Thank you very much for the help!

Melden Sie sich an, um diese Frage zu beantworten.

Akzeptierte Antwort

Greg Heath
Greg Heath am 29 Nov. 2013
1. Probably (I've forgotten the definition of a finite state machine, but the NN is a universal approximator)
2. The net is not a mind reader. It learns via samples from representative I/O examples. As far as it is concerned, [ umin, umax ] is determined by training data. Remember, the default neural net approximation is a linear superposition of bounded tanh functions.
3. The three largest problems with neural networks:
a. They cannot read minds.
b. They cannot program themselves.
c. They must rely on humans.
HTH
Thank you for formally accepting my answer
Greg
  2 Kommentare
Yiming
Yiming am 29 Nov. 2013
Bearbeitet: Yiming am 29 Nov. 2013
Hi Greg,
thanks for your reply.
1. I am thinking of finite-state machine is because that I've been wondering how a NN deals with a new input. Let's assume that I have only one input and the input space is finite like u = [u1,u2,u3,u4,u5] and it follows that u1<u2<u3<u4<u5. If I just train the network with a data set concluding u1,u2,u4,u5, how does the NN deal with a input u3? Is this output reliable? What about a multiple-input case?
2. Do you think if I manually convert both input and output spaces into finite will improve the performance of this NN? For instance, if I have both continuous input and output spaces as [0 10] and [10 20], I can manually convert all inputs and outputs into integers, then the input and output spaces will become [0 1 2 3 4 5 6 7 8 9 10] and [10 11 12 13 14 15 16 17 18 19 20]. Do you think it help?
Right now I am really messed up by NN and some other nonlinear system identification stuff. I hope these questions are not too stupid.
Thank you so much for your help!
Yiming
Greg Heath
Greg Heath am 30 Nov. 2013
1. I would have much more confidence in the result from input u3 than the result from either u0 or u6. There is no guarantee and should be no expectation that a net that interpolates well in the subspace spanned by the training data will extrapolate well outside of that subspace.
The exception, of course is a well trained time-series with well established significant output auto or output/input cross correlations.
2. The ranges of the input and output spaces for a NN are defined by the training data, not the full space from which the training data was obtained.
3. The best way to answer your questions is to try a test case and, if there are questions, post code, comments and error messages.
HTH

Melden Sie sich an, um zu kommentieren.

Weitere Antworten (0)

Kategorien

Mehr zu Sequence and Numeric Feature Data Workflows finden Sie in Help Center und File Exchange

Tags

Community Treasure Hunt

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

Start Hunting!

Translated by