hello sir, pamho,
I am working on bio metric identification system, with 512 features of 80 identities as enrollment data,so my input for neural network is 512*80 matrix. But i can't decide what should be given as target so that system can identify enrolled 80 person and reject others. Please help.

 Réponse acceptée

Greg Heath
Greg Heath le 19 Avr 2015

0 votes

You cannot define a 512 dimensional input space with 80 examples.
Therefore, use feature extraction to substantially reduce the number of features.
The target vectors should be {0,1} 80-dimensional unit vectors.
Hope this helps.
Greg

Plus de réponses (0)

Catégories

En savoir plus sur Deep Learning Toolbox dans Centre d'aide et File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by