| R.S. Michalski. A theory and methodology of inductive learning. Arti cial Intelligence, 20:pp111-161, 1983. |
....deserves special attention here as it is one of the overlooked issues in rule extraction techniques and also because to some extent this notion is useful in characterizing the di erence between inductive and analytical learning. The importance of this criterion is argued by Michalski [40] in his comprehensibilty postulate: The results of computer induction should be symbolic descriptions of given entities, semantically and structurally similar to those a human expert might produce observing the same entities. Components of these descriptions should be comprehensible as single ....
Michalski R. S. A theory and methodology of inductive learning. Arti- cial Intelligence, 20:111-161, 1983.
....(EBL) 26] while the aim of the inductive subcomponent is to incrementally re ne it. However, we have found out that Hamlet does not always generate more accurate control knowledge by observing more and more examples. We suspect that this is due to its example driven operators (like AQ s [24]) This means that the only way Hamlet can re ne current control knowledge is by being presented the proper set of examples. Unfortunately, if the examplespace is large, it could take Hamlet very long to generate correct control knowledge. Additionally, as Hamlet EBL subcomponent learns from ....
Ryszard S. Michalski. A theory and methodology of inductive learning. Arti cial Intelligence, 20, 1983.
No context found.
R.S. Michalski. A theory and methodology of inductive learning. Arti cial Intelligence, 20:pp111-161, 1983.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC