How to initialize target matrix of a Neural-Network ?
1 visualización (últimos 30 días)
Mostrar comentarios más antiguos
Hello, My question is :-
1. For PCA and Eigenbased Face Recognition, I am reshaping 30 images into a 2D array where each row of the 2-D matrix denotes the vectors of a single face. My question is :- for generating the training vector set, how should I initialize the target vector of ANN(Artificial Neural network)so that I can perform the recognition correctly ? Any help would be appreciated and thank you in advance.
With regards, Ampi B.
0 comentarios
Respuesta aceptada
Greg Heath
el 24 de Oct. de 2012
I assume you are using patternnet.
Your N I-dimensional input vectors should be columns (not rows) of an IxN input matrix.
For c classes, your N c-dimensional target vectors should be columns of a cXN target matrix. The target vectors should be columns of the c-dimensional unit matrix eye(c). The row index of the "1" is the class index of the corresponding input vector.
Hope this helps.
Thank you for formally accepting my answer.
Greg
0 comentarios
Más respuestas (1)
Ver también
Categorías
Más información sobre Dimensionality Reduction and Feature Extraction en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!