2
$\begingroup$

I have the following data

         feat_1    feat_2 ... feat_n   label
gene_1   100.33     10.2  ... 90.23    great
gene_2   13.32      87.9  ... 77.18    soso
....
gene_m   213.32     63.2  ... 12.23    quite_good

The size of M is large ~30K rows, and N is much smaller ~10 columns. My question is what is the appropriate Deep Learning structure to learn and test the data like above.

At the end of the day, the user will give a vector of genes with expression.

gene_1   989.00
gene_2   77.10
...
gene_N   100.10

And the system will label which label does each gene apply e.g. great or soso, etc...

By structure I mean one of these:

  • Convolutional Neural Network (CNN)
  • Autoencoder
  • Deep Belief Network (DBN)
  • Restricted Boltzman Machine
$\endgroup$
0
$\begingroup$

I suggest that a feedforward Neural Network with 1 or more hidden layers should be appropriate for a binary or multiclass problem.

I should also point out that with a relatively smaller number of features (10) compared to M, other classifiers such as Logistic regression / Random Forests should give acceptable performance and would train faster as well.

$\endgroup$
  • 1
    $\begingroup$ What rationale is your suggestion based upon? $\endgroup$ – naught101 Sep 26 '16 at 1:27

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.