0
$\begingroup$

Nowadays i am doing a research project where i am allowed to classify given a sample from a large dataset with an already existed sample/target model the belonging target, but in my project there are more outputs beyond the mainly ones, for example on the figure below:

enter image description here

Ex:

sample[0]:
x_sample content: [[0.2786815  0.7681137  0.13595986 0.28324878 0.29709998 0.88603574
  0.4820799  0.41181254 0.1778333  0.37944523]
 [0.08139297 0.55912787 0.8396389  0.8993042  0.6727391  0.546429
  0.16076903 0.7361717  0.6788026  0.11437038]
] #and so on...

and target like for example:

>>e1 = np.zeros((2, 1))
>>e2 = np.zeros((5, 1))
>>e3 = np.zeros((1, 1))
>>e = np.array([e1,e2,e3])
>>e[0][0] = 1.0
>>e[1][2] = 1.0
e
# Vertebrate AND fish
    array([array([[1.],
           [0.]]),
           array([[0.],
           [0.],
           [1.],
           [0.],
           [0.]]),
           array([[0.]])], dtype=object)

I already have an algorithm to classify data with four neurons from 0 to 4 with a MLP neural network based in single array, now i am in doubt if is there any neural network that is possible to classify subtargets from main targets with nested arrays?

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.