I am solving multi-label classification problem (assigning each image 1 to N labels) and want to use neural network (like in this post). Does this approach take correlations between class labels into account? Or are the predictions for individual labels completely independent (like in the binary relevance approach)?

  • 1
    $\begingroup$ Please add details and context about your classification problem Multi-label classification is ambiguous: are you assigning one label to each sample, or possibly multiple ones? If it's the former, then a softmax is the way to go as everything would add up to 1. So classes would be correlated during training. $\endgroup$ – Alex R. Feb 12 at 20:57
  • $\begingroup$ Multiple ones, I've edited the question. $\endgroup$ – Miroslav Sabo Feb 12 at 21:25

For sure correlation is taken into account since your hidden layer mixing all signals from input together via fully connected layer. Your network will learn about co-occurrence of labels, however it's done in not-random way, I meant your network would find some deterministic rules for generating the best output. Be aware that this only 'projection' of statistical correlation into NN's linear space forced by your NN's optimization function. You won't have any direct influence on that


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.