Open ChewyMoon opened 9 years ago
Great question. In this case the machine learning problem will not accept a multi-valued output (hence no support for en EnumerableLabel). What are you trying to accomplish? Maybe I've made a mistake somewhere.
I do think at least a vector output should be supported.
I don't think the intent is to make any arbitrary graph into a potentially significantly sparse array of vectors. Or am I missing something too? On Jun 11, 2015 10:24 AM, "Justin" notifications@github.com wrote:
I do think at least a vector output should be supported.
— Reply to this email directly or view it on GitHub https://github.com/sethjuarez/numl/issues/28#issuecomment-111153393.
@ChewyMoon I'm interested in a use case. I might be missing something (maybe it's something we should support).
Just saw this, a use case would be learning sequences. Such as in one to many or many to many recurrent neural nets.
Sounds good. A couple of things moving forward:
I'm nearly finished with SVM, scoring, multi-class learning (it handles unlimited classes, with support for using any generator and is parallelised by n classes), recommendation (collaborative filtering) and started with recurrent neural nets. It should be fairly straight forward to implement sequence learning as all you are doing is changing the predicted output to a vector and the vector size would be set from either a labelenumerable attribute or the size of the output layer in a neural net.
OK - we should meet about the code. Some of the previous stuff we've merged seems to duplicate some of the other math structures available. Maybe we should have a face-to-face to make sure I am understanding properly. I also want to move to a unified data structure for all models (some graph type data structures). What do you think? Perhaps we should move the convo to gitter:
Reopening issue.
This is partially implemented, see ISequenceModel and Neural Networks.
We need to discuss for other algorithms...
Any label that implements the IEnumerable will throw exceptions saying that it needs to have the EnumerableFeature attribute, when I need a Label, not a Feature.