We usually categorize objects in a hierarchy of classes. Let us say crow vs bird. In addition, classes can be "messy", for instance a crow can be also a predator, but not all birds are predators.

My question is, can deep networks represent these hierarchies easily? Has anybody studied that? (I could not find anything at all).


In this case, you have an ontology and want to learn the ontology. There are many researches in this topic that you can find. However, the data could be the most challenging part. Some of the researches:

Also, as these are some frameworks to ontology learning, you can use deep networks such as RNN‌ to learn the task.

  • $\begingroup$ +1 but it does not seem related to my question though. My questions was it is implementable in deep convolutional networks $\endgroup$ – Wolphram jonny Nov 30 '19 at 0:46

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.