MATLAB: Neural Netwok testing issues

Deep Learning Toolboxzero output

I am a beginner on neural networks and working on a project in which I am supposed to recognize a face of a person. I have developed a code and train the network on NN toolbox with the specific data base(5 people each having 10 samples).

During test when I provide one of the picture from data base(through which I have trained the network) it works correctly( gives me 1 or 0.99 value in output on the specific person)

But my problem is this when I provide it a random pic whose dimensions are same it never gives zero output for all the faces(those 5).

Best Answer

Bottom lime:

You don't have enough data to adequately characterize a space of dimension 10,304.

50 data points can span, AT MOST, 49 dimensions.

Use feature extraction to drastically reduce input dimensions.

Try searching the NEWSGROUP and ANSWERS for ways to extract features from face images

Hope this helps.

Greg

Related Solutions

MATLAB: Bad classification even after training neural network

Two possibilities

 1. The training data does not adequately characterize the total data set.
 2. The net is overfit with too many weights AND the net is overtrained past the point where it  
    trades the ability to work well on nontraining data to further the decrease in training error.

Are you using validation stopping?

Are your training, validation and test sets randomly chosen?

What are the data division ratios?

Hope this helps.

Thank you for formally accepting my answer

Greg

MATLAB: Using a 2 dimensional feature

Every place that you index classTwoTestData(some_index) you need to change it to classTwoTestData(some_index,:) and likewise for similar variables.

You also need to adjust your euclidean distance calculations. A(index,:) - B(index,:) will be a vector, so you cannot use ^2 for it: you need to use .^2 . You also need to take the sum of the squared components.

Best Answer

Related Solutions

MATLAB: Bad classification even after training neural network

MATLAB: Using a 2 dimensional feature

Related Question