ontolog-forum
[Top] [All Lists]

Re: [ontolog-forum] ID3 and other decision trees

To: "'[ontolog-forum] '" <ontolog-forum@xxxxxxxxxxxxxxxx>
From: "Rich Cooper" <rich@xxxxxxxxxxxxxxxxxxxxxx>
Date: Wed, 4 Jun 2014 08:06:41 -0700
Message-id: <34C5A597838B4C36BEFBE43D8E7B53D6@Gateway>

Thanks Leo,

 

Yes, I remember thinking decision trees were simple versions of classification methods, and nearest neighbor was the most general of all distinctions to make in those days.  I remember a pattern recognition course in grad school that was loads of fun.  But back then, it only dealt with numeric and enumerative domains, not with NLP aspects at all. 

 

-Rich

 

Sincerely,

Rich Cooper

EnglishLogicKernel.com

Rich AT EnglishLogicKernel DOT com

9 4 9 \ 5 2 5 - 5 7 1 2


From: ontolog-forum-bounces@xxxxxxxxxxxxxxxx [mailto:ontolog-forum-bounces@xxxxxxxxxxxxxxxx] On Behalf Of Obrst, Leo J.
Sent: Wednesday, June 04, 2014 5:22 AM
To: [ontolog-forum]
Subject: Re: [ontolog-forum] ID3 and other decision trees

 

A bit tangentially, also see binary decision diagrams (BDDs) for boolean functions, e.g., and the references at: http://en.wikipedia.org/wiki/Binary_decision_diagram. I think the first time I came across these was in the ACM survey paper of Bryant (1992): http://www.cs.cmu.edu/~bryant/pubdir/acmcs92.ps.

 

We had originally used decision trees (not automated induction of these, however) back in my COBOL days of the early 1980s.

 

Thanks,

Leo

 

 

From: ontolog-forum-bounces@xxxxxxxxxxxxxxxx [mailto:ontolog-forum-bounces@xxxxxxxxxxxxxxxx] On Behalf Of Philip Jackson
Sent: Wednesday, June 04, 2014 6:41 AM
To: [ontolog-forum]
Subject: Re: [ontolog-forum] ID3 and other decision trees

 

Suggesting a new title for this thread, since Rich's first question

 

> >> Has anyone used ID3 to identify classes in clustering analysis?

was about a more narrow topic that human-level AI. 

 

Thanks to Chris Mungall for the link to a summary of differences between decision trees.

 

Phil

> From: cjmungall@xxxxxxx
> To: ontolog-forum@xxxxxxxxxxxxxxxx
> Date: Tue, 3 Jun 2014 18:22:33 -0700
> Subject: Re: [ontolog-forum] Toward Human-Level AI
>
> A good summary:
>
> http://stackoverflow.com/questions/9979461/different-decision-tree-algorithms-with-comparison-of-complexity-or-performance
>
>
> On 3 Jun 2014, at 17:56, Rich Cooper wrote:
>
> > After reading C4.5, it seems nearly identical to
> > ID3. What exactly is the difference?
> >
> > Sincerely,
> > Rich Cooper
> > EnglishLogicKernel.com
> > Rich AT EnglishLogicKernel DOT com
> > 9 4 9 \ 5 2 5 - 5 7 1 2
> >
> > -----Original Message-----
> > From: ontolog-forum-bounces@xxxxxxxxxxxxxxxx
> > [mailto:ontolog-forum-bounces@xxxxxxxxxxxxxxxx] On
> > Behalf Of Jack Park
> > Sent: Tuesday, June 03, 2014 5:11 PM
> > To: [ontolog-forum]
> > Subject: Re: [ontolog-forum] Toward Human-Level AI
> >
> > FWIW, I implemented ID3 in Forth back in around
> > 1984 to support a
> > friend's thesis research; it was used to evaluate
> > comments made by
> > manufacturing engineers on process control.
> >
> > An issue it raised, which has been mentioned in
> > the literature, is
> > that it grew rather complex, bushy decision trees.
> > I think that might
> > be a part of the reason for migration to C4.5
> > http://en.wikipedia.org/wiki/C4.5_algorithm
> >
> >
> > On Sun, Jun 1, 2014 at 9:32 AM, Rich Cooper
> > <rich@xxxxxxxxxxxxxxxxxxxxxx> wrote:
> >> Here is a link to the ID3 algorithm by Ross
> > Quinlan:
> >>
> >> http://en.wikipedia.org/wiki/ID3_algorithm
> >>
> >>
> >>
> >> The algorithm iteratively divides the elements
> > of S based on all attribute
> >> values of all objects, which are said elements
> > of S. So it picks the group
> >> of features and weights that make the most
> > "efficient" split. That
> >> separates S into S0 and S1. Its use of the
> > "entropy" analogy to evaluate
> >> efficiency of the split seems a bit of
> > anthropopathy.
> >>
> >>
> >>
> >> Has anyone used ID3 to identify classes in
> > clustering analysis?
> >>
> >>
> >>
> >> -Rich
> >>
> >>
> >>
> >> Sincerely,
> >>
> >> Rich Cooper
> >>
> >> EnglishLogicKernel.com
> >>
> >> Rich AT EnglishLogicKernel DOT com
> >>
> >> 9 4 9 \ 5 2 5 - 5 7 1 2
> >>
> >>
> >>
> >>
> > __________________________________________________
> > _______________
> >> Message Archives:
> > http://ontolog.cim3.net/forum/ontolog-forum/
> >> Config Subscr:
> > http://ontolog.cim3.net/mailman/listinfo/ontolog-f
> > orum/
> >> Unsubscribe:
> > mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
> >> Shared Files: http://ontolog.cim3.net/file/
> >> Community Wiki: http://ontolog.cim3.net/wiki/
> >> To join:
> > http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePa
> > ge#nid1J
> >>
> >
> > __________________________________________________
> > _______________
> > Message Archives:
> > http://ontolog.cim3.net/forum/ontolog-forum/
> > Config Subscr:
> > http://ontolog.cim3.net/mailman/listinfo/ontolog-f
> > orum/
> > Unsubscribe:
> > mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
> > Shared Files: http://ontolog.cim3.net/file/
> > Community Wiki: http://ontolog.cim3.net/wiki/
> > To join:
> > http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePa
> > ge#nid1J
> >
> >
> >
> > _________________________________________________________________
> > Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
> > Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/
> > Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
> > Shared Files: http://ontolog.cim3.net/file/
> > Community Wiki: http://ontolog.cim3.net/wiki/
> > To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J
>
> _________________________________________________________________
> Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/
> Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/
> Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
> Shared Files: http://ontolog.cim3.net/file/
> Community Wiki: http://ontolog.cim3.net/wiki/
> To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J
>


_________________________________________________________________
Message Archives: http://ontolog.cim3.net/forum/ontolog-forum/  
Config Subscr: http://ontolog.cim3.net/mailman/listinfo/ontolog-forum/  
Unsubscribe: mailto:ontolog-forum-leave@xxxxxxxxxxxxxxxx
Shared Files: http://ontolog.cim3.net/file/
Community Wiki: http://ontolog.cim3.net/wiki/ 
To join: http://ontolog.cim3.net/cgi-bin/wiki.pl?WikiHomePage#nid1J    (01)

<Prev in Thread] Current Thread [Next in Thread>