How to set target vector (with large data set) for neural network?

2 visualizaciones (últimos 30 días)
How can I classify targets with a large set of data/values (37539840 x 1)? I have tried using the Neural Network but I am unable to set the target class using 1 and 0 given the large data/values.

Respuesta aceptada

Greg Heath
Greg Heath el 28 de Mzo. de 2014
Regardless of data values, use MAPSTD or ZSCORE and training data to normalize inputs.
For c classes, the target matrix should contain columns of the unit matrix eye(c). The relationship between integer class indices 1:c and target vectors are given by functions ind2vec and vec2ind.
You have so much data, you only need a small fraction of it to design a net, or even multiple nets.
Hope this helps.
Thank you for formally accepting my answer
Greg

Más respuestas (0)

Categorías

Más información sobre Sequence and Numeric Feature Data Workflows 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!

Translated by