1
$\begingroup$

I am working with this dataset which is record of student academic details and I want to predict the student's performance.

since the dataset is non-continuous I cannot apply CNN on this dataset.

How can I apply Deep learning on this kind(non-continuous) of dataset. I searched online but could not find anything relevant

Thank you!!

$\endgroup$
1
  • 1
    $\begingroup$ Your dataset consists of only 649 instances, a neural network requires more data to train. You should consider using different methods for analyzing this dataset, for instance linear regression, decision tree, random forrest, XGBoost, KNN... $\endgroup$ – Geert Immerzeel Oct 28 '19 at 10:19
3
$\begingroup$

Deep Learning excels in problems where the data is relatively unstructured. Stacked layers help find conceptual features that can be used to infer rules.

Your dataset seems very structured at first glance. And, as you pose, it doens't look like it needs specialised layers that exploit sequential or spatial relations.

Neural network wise, this would warrant one or two fully connected layers, connected to an output layer (shaped to your wishes). However, typically, problems like these are tackled with a more biased approaches (eg Decision Tree Learners).

$\endgroup$
2
  • $\begingroup$ So that means i cannot apply neural networks on this particular dataset $\endgroup$ – Sachin Yadav Oct 28 '19 at 11:23
  • $\begingroup$ You can, but you might want to try something else. BTW: I described an approach with two FC-layers, I have read papers that called that Deep Learning (but it isn't) $\endgroup$ – S van Balen Oct 29 '19 at 10:58

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.