Re: DM: Datamining Definition...and Machine Learning Definition.

Thank you Santro. This seems to be what the University of East Anglia is
saying more succintly on its web site,
http://www.sys.uea.ac.uk/PGStudy/mscke.htm re the MSc in knowledge
extraction which it defines as "extracting knowledge from larger databases".
I used the word "text" below because I thought the word "database" might be
too broad. The whole universe is a data base in a sense...mountainous for
sure.
If we go with such a broad term then data mining/knowledge extraction
becomes synonymous with machine learning does it not? Would an Msc in
machine learning then be the same as an Msc in data extraction? The other
web site given was http://www.cs.bris.ac.uk/Teaching/MachineLearning .
Elsewhere I have come up with 11 categories of machine learning and I will
forward them to the list later. "Learning from text" would be one category.
I think most people would want machine learning to stand for a much broader
field than data mining/knowledge extraction.
    What I am trying to get at with "learning from text" is that this is one
of the most common and incredibly complex ways in which humans learn.
Imagine any text book.
It contains as you note below, words, numbers, symbols and pictures. The
same information can be presented by the teacher in a classroom ; the text
is turned into an oral presentation. If I could speed through text books
without assistance from teachers I would quickly become the most learned
person in the world. It is quite amazing that students extract the
"noteworthy" or "valuable" material from all of this information.
I think phrases like data mining and knowledge extraction may communicate
better with cs specialists but "learning from text" may communicate better
outside this field.
It sounds very much to me at this stage that we would mean the same thing.
After a lot of reading texts and going to lectures where the texts are
explained, elaborated on etc. the medical student extracts the noteworthy
data on how to do medical diagnoses. Now what would it do to medical
training if the student could use a
computer/robot to extract the same "hidden knowledge" from the "larger
databases" of the medical texts, lectures etc.?
    Before even trying to answer that question I want to make sure we have
pretty good agreement on the definition. Also would you agree that data
mining is one kind of machine learning? Here is another: maze learning. I
think machines have this one mastered do they not? The algorithms for maze
learning are quite simple compared to those for data mining are they not? I
wonder then which category of machine learning we would place at one end of
that simple-complex continuum and which we would place at the other?
FWP.

-----Original Message-----
From: Santrokofi <santrokofi@yahoo.com>
To: datamine-l@nautilus-sys.com <datamine-l@nautilus-sys.com>
Date: Wednesday, March 22, 2000 9:28 PM
Subject: Re: DM: Datamining Definition.

 >Hi Franklin,
 >
 >I hope this definition helps:
 >
 >"Data mining explores mountainous databases, using
 >automated approaches, to reveal meaningful patterns.
 >  The databases may contain numbers, words, graphs, or
 >pictures.   Data from these different sources can be
 >pooled into data warehouses.  Data mining algorithms
 >can then examine numerous multidimensional data
 >relationships concurrently, highlighting those that
 >are noteworthy."
 >
 >Santro Kofi
 >
 >--- Franklin Wayne Poley <culturex@vcn.bc.ca> wrote:
 > >
 > > Could datamining be fairly defined as "extracting
 > > data of value from
 > > text"? (With "text" broadly defined to include
 > > words, sentences, pictures,
 > > symbols etc?
 > > FWP.
 > >
 >http://users.uniserve.com/~culturex/Machine-Psychology.htm

• Follow-Ups:
  • Re: DM: Datamining Definition...and Machine Learning Definition.
    • From: Warren Sarle
  • DM: New PhD seeks DFW data mining/statistical work
    • From: Dr. Scott Nicholson

• Prev by Date: Re: DM: Datamining Definition.
• Next by Date: DM: [Robot-for-President] Machine Learning Taxonomy (fwd)
• Prev by thread: DM: [Robot-for-President] Machine Learning Taxonomy (fwd)
• Next by thread: DM: New PhD seeks DFW data mining/statistical work
• Index(es):
  • Date
  • Thread