How to train a Neural Network to give me a classified output based on male or female?
1 次查看(过去 30 天)
显示 更早的评论
In my project I have two vectors of [200x1] that should be used in Neural Network and trained in a way that it gives me the subject's fingerprint gender.
I think I should provide a target vector based on the subject's gender from the ground truth data (like 1 for female and 0 for male) But I am not sure if this consideration is correct.
Any idea for this?
0 个评论
采纳的回答
Greg Heath
2014-4-23
1. Two vectors are insufficient. Look at typical input/target sizes for classifiers
help nndatasets
doc nndatasets
2. 200 dimensional inputs probably have many that are insignificant. Dimensionality reduction is recommended.
3. {0,1} targets are fine.
Hope this helps.
Thank you for formally accepting my answer
Greg
0 个评论
更多回答(0 个)
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!