You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by Sean Owen <sr...@gmail.com> on 2009/10/03 16:12:01 UTC

TLA clarifications

Hi I'm running into several TLAs (three letter acronyms) in the book
outline that I am not sure I know. Help me define:

SVM = Support Vector Machine?
LR = ?
AUC = ?
LDA = Linear Discriminant Analysis?
CBayes = Constrained Bayes? no idea actually

Re: TLA clarifications

Posted by Isabel Drost <is...@apache.org>.
On Saturday 03 October 2009 21:34:16 Ted Dunning wrote:
> In our context, the latent dirichlet allocation is a much higher
> probability interpretation.

A more detailed explanation in our wiki:

http://cwiki.apache.org/MAHOUT/latent-dirichlet-allocation.html

Isabel

-- 
  |\      _,,,---,,_       Web:   <http://www.isabel-drost.de>
  /,`.-'`'    -.  ;-;;,_  
 |,4-  ) )-,_..;\ (  `'-' 
'---''(_/--'  `-'\_) (fL)  IM:  <xm...@spaceboyz.net>


Re: TLA clarifications

Posted by Ted Dunning <te...@gmail.com>.
In our context, the latent dirichlet allocation is a much higher probability
interpretation.

On Sat, Oct 3, 2009 at 10:35 AM, Jake Mannix <ja...@gmail.com> wrote:

> On Sat, Oct 3, 2009 at 7:12 AM, Sean Owen <sr...@gmail.com> wrote:
>
> LDA = Linear Discriminant Analysis?
> >
>
> Of course, LDA can also mean Latent Dirichlet Allocation, but I'm sure
> you were already aware of that, given that we have such an impl in Mahout.
>
>  -jake
>



-- 
Ted Dunning, CTO
DeepDyve

Re: TLA clarifications

Posted by Jake Mannix <ja...@gmail.com>.
On Sat, Oct 3, 2009 at 7:12 AM, Sean Owen <sr...@gmail.com> wrote:

LDA = Linear Discriminant Analysis?
>

Of course, LDA can also mean Latent Dirichlet Allocation, but I'm sure
you were already aware of that, given that we have such an impl in Mahout.

  -jake

Re: TLA clarifications

Posted by Ted Dunning <te...@gmail.com>.
Complementary Bayes, I think.  More normally Complementary Naive Bayesian.

On Sat, Oct 3, 2009 at 7:50 AM, Vaclav Petricek <v....@gmail.com>wrote:

> > CBayes = Constrained Bayes? no idea actually
>
> not sure - don't know the cotext




-- 
Ted Dunning, CTO
DeepDyve

Re: TLA clarifications

Posted by Vaclav Petricek <v....@gmail.com>.
On Sat, Oct 3, 2009 at 3:12 PM, Sean Owen <sr...@gmail.com> wrote:
> Hi I'm running into several TLAs (three letter acronyms) in the book
> outline that I am not sure I know. Help me define:
>
> SVM = Support Vector Machine?

yes

> LR = ?

LR = Likelihood ratio but could be Linear Regression, Logistic
Regression depending on context

> AUC = ?

AUC = Area Under (ROC) Curve
ROC = Receiver Operating Characteristic
http://en.wikipedia.org/wiki/Receiver_operating_characteristic

> LDA = Linear Discriminant Analysis?

yes

> CBayes = Constrained Bayes? no idea actually

not sure - don't know the cotext

Venca

Re: TLA clarifications

Posted by Robin Anil <ro...@gmail.com>.
>
>
> > CBayes = Constrained Bayes? no idea actually
>
> Robin?
>
> Complementary Naive Bayes

Re: TLA clarifications

Posted by Isabel Drost <is...@apache.org>.
On Saturday 03 October 2009 16:12:01 Sean Owen wrote:
> Hi I'm running into several TLAs (three letter acronyms) in the book
> outline that I am not sure I know. Help me define:
>
> SVM = Support Vector Machine?

Jepp.

> LR = ?

Probably Logistic Regression - generally used for classification.


> AUC = ?

Area under ROC - ROC - receiver operator characteristic: 

http://en.wikipedia.org/wiki/Receiver_operating_characteristic


> LDA = Linear Discriminant Analysis?

Yes.


> CBayes = Constrained Bayes? no idea actually

Robin?

Cheers,
Isabel

-- 
QOTD: Anyone willing and capable to get themselves elected President by no 
means should be allowed to do the job.                 -- Douglas Adams 
  |\      _,,,---,,_       Web:   <http://www.isabel-drost.de>
  /,`.-'`'    -.  ;-;;,_  
 |,4-  ) )-,_..;\ (  `'-' 
'---''(_/--'  `-'\_) (fL)  IM:  <xm...@spaceboyz.net>


Re: TLA clarifications

Posted by Grant Ingersoll <gs...@apache.org>.
On Oct 3, 2009, at 10:12 AM, Sean Owen wrote:
>
> CBayes = Constrained Bayes? no idea actually

Complementary Bayes.