addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwchatcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscrosseditemptyheartfacebookfolderfullheartglobegmailgoogleimagesinstagramlinklocation-pinmagnifying-glassmailminusmoremuplabelShape 3 + Rectangle 1outlookpersonplusprice-ribbonImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruseryahoo
Noman A.
user 69878802
San Francisco, CA
Post #: 1
Hi All,

I am working on unsupervised learning using neural networks. I need help in R to implement the same. Can someone help me on this.

Noman Ahmed
Robert M. Horton, ...
user 12069592
San Francisco, CA
Post #: 4
Can you provide a sample problem?
Noman A.
user 69878802
San Francisco, CA
Post #: 2
Basically I am trying to solve clustering problem and as far as I know there are some packages like som, kohenen, class etc. but again can someone show me the results with an example.
Mike W.
San Francisco, CA
Post #: 3
Hi Norman,

I apologize that I cannot be more helpful, and it seems that others cannot, either, but the reason is because your question is overly broad.
For instance, I have used clustering algorithms at times, but the entire code is quite complex, mostly because any code put into a "real world" example is dominated by data collection and manipulation. In any bit of code I've written that is, say 1000 lines, maybe about 100 of them would be the core "fancy math" that you have in question.
So how could I give you an example? I could send you a .R file, but most of it would not apply. I could either generate or send you snippets of the core parts of the clustering algo, but I don't know what you'd consider the core parts because I am not sure where your confusion lies.

For me, and I suspect for others, it'd help if you added some information, like:
o What algorithms are you considering, and why? (You can go to the r-project website to search for the packages available.)
o After looking through the help on whichever package you choose and trying some of the examples, where are you having trouble?
o Which part of your unsupervised learning are you having trouble with? Finding a reasonable data set to practice with? Problems with the quality of data in your set (e.g., too many NULL or invalid values)? Understanding the core concepts?

The more info you provide, the better the answers you receive can be. I don't say that to sound "soapbox-y", just to make it clear that your question, as posed, is challenging to answer.


Powered by mvnForum

Our Sponsors

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy