how to use neural network to tell true or false of a realtime input?
in [Matlab]
|
Prev: extrapolating a point
Next: Using dynamic Bayesian networks with transcriptional regulation in Murphy's BNT program
From: Simeon on 19 Jul 2010 14:44 Problem description: A neural network is needed by the psychology lab to determine whether the subject gives right response to the features of the given object. all data in this problem is taken from N dimension feature space, e.g, [shape,size,color] for given objects. the intensity of each dimension is digitalized to [1,10]. Training data is given (MxN matrix). A neural network will be trained with the given data. After training, the network should give positive response when the most frequent feature vector is given from input. The critical part is, after trained with given data, "the most frequent feature vector" might keep changing because the subject might gives different response other than the "the most frequent feature vector" we got from the training data. How to make the network keeps updating? Any suggestion is appreciated.
From: Simeon on 20 Jul 2010 06:01 anybody？ please "Simeon " <simeonyu1981(a)yahoo.com> wrote in message <i226dl$jc7$1(a)fred.mathworks.com>... > Problem description: > A neural network is needed by the psychology lab to determine whether the subject gives right response to the features of the given object. > > all data in this problem is taken from N dimension feature space, e.g, [shape,size,color] for given objects. the intensity of each dimension is digitalized to [1,10]. > > Training data is given (MxN matrix). A neural network will be trained with the given data. After training, the network should give positive response when the most frequent feature vector is given from input. > > The critical part is, after trained with given data, "the most frequent feature vector" might keep changing because the subject might gives different response other than the "the most frequent feature vector" we got from the training data. > How to make the network keeps updating? > > Any suggestion is appreciated.
From: Steven_Lord on 20 Jul 2010 09:15 "Simeon " <simeonyu1981(a)yahoo.com> wrote in message news:i23s50$3vv$1(a)fred.mathworks.com... > anybody？ please > > "Simeon " <simeonyu1981(a)yahoo.com> wrote in message > <i226dl$jc7$1(a)fred.mathworks.com>... >> Problem description: >> A neural network is needed by the psychology lab to determine whether the >> subject gives right response to the features of the given object. >> >> all data in this problem is taken from N dimension feature space, e.g, >> [shape,size,color] for given objects. the intensity of each dimension is >> digitalized to [1,10]. >> >> Training data is given (MxN matrix). A neural network will be trained >> with the given data. After training, the network should give positive >> response when the most frequent feature vector is given from input. >> >> The critical part is, after trained with given data, "the most frequent >> feature vector" might keep changing because the subject might gives >> different response other than the "the most frequent feature vector" we >> got from the training data. How to make the network keeps updating? >> >> Any suggestion is appreciated. So you want your network to keep training with the new information? Then TRAIN it again, using your original training data as well as the new data. You probably only want to do this after you've collected some number of new data points, rather than retraining every time a new data point comes in. -- Steve Lord slord(a)mathworks.com comp.soft-sys.matlab (CSSM) FAQ: http://matlabwiki.mathworks.com/MATLAB_FAQ To contact Technical Support use the Contact Us link on http://www.mathworks.com
From: Greg Heath on 20 Jul 2010 11:01 On Jul 19, 2:44 pm, "Simeon " <simeonyu1...(a)yahoo.com> wrote: > Problem description: > A neural network is needed by the psychology lab to determine whether the subject gives right response to the features of the given object. > > all data in this problem is taken from N dimension feature space, e.g, [shape,size,color] for given objects. the intensity of each dimension is digitalized to [1,10]. > > Training data is given (MxN matrix). A neural network will be trained with the given data. After training, the network should give positive response when the most frequent feature vector is given from input. > > The critical part is, after trained with given data, "the most frequent feature vector" might keep changing because the subject might gives different response other than the "the most frequent feature vector" we got from the training data. > How to make the network keeps updating? > > Any suggestion is appreciated. Suggestions are size and time dependent. What are M(number of input variables) and N(Number of observations/cases)? How often will you be updating the model? How many observations per update? If N is huge and updates are large and frequent, it may be prudent to maintain a smaller calibration set that summarizes the salent characteristics of past data. Typically, this can be obtained by intially clustering the training data and using cluster centers as the calibration set. When new data is encountered, both the calibration set and the net are updated. Hope this helps. Greg
From: Simeon on 21 Jul 2010 23:06
Thanks for the reply. The problem is: the new input from the subjects keeps coming in, there is no time to "Train it again". I am wondering whether there is a better way to do the two tasks simultaneously: 1. tell weather the current input is ture ("the most frequent feature vector" ) 2. update the network Thanks again. "Steven_Lord" <slord(a)mathworks.com> wrote in message <i247i3$24r$1(a)fred.mathworks.com>... > > > "Simeon " <simeonyu1981(a)yahoo.com> wrote in message > news:i23s50$3vv$1(a)fred.mathworks.com... > > anybody？ please > > > > "Simeon " <simeonyu1981(a)yahoo.com> wrote in message > > <i226dl$jc7$1(a)fred.mathworks.com>... > >> Problem description: > >> A neural network is needed by the psychology lab to determine whether the > >> subject gives right response to the features of the given object. > >> > >> all data in this problem is taken from N dimension feature space, e.g, > >> [shape,size,color] for given objects. the intensity of each dimension is > >> digitalized to [1,10]. > >> > >> Training data is given (MxN matrix). A neural network will be trained > >> with the given data. After training, the network should give positive > >> response when the most frequent feature vector is given from input. > >> > >> The critical part is, after trained with given data, "the most frequent > >> feature vector" might keep changing because the subject might gives > >> different response other than the "the most frequent feature vector" we > >> got from the training data. How to make the network keeps updating? > >> > >> Any suggestion is appreciated. > > So you want your network to keep training with the new information? Then > TRAIN it again, using your original training data as well as the new data. > You probably only want to do this after you've collected some number of new > data points, rather than retraining every time a new data point comes in. > > -- > Steve Lord > slord(a)mathworks.com > comp.soft-sys.matlab (CSSM) FAQ: http://matlabwiki.mathworks.com/MATLAB_FAQ > To contact Technical Support use the Contact Us link on > http://www.mathworks.com |