Information Technology Reference
In-Depth Information
c
1
c
ϖ
]
T
Definition 7.15
represents cost to get every
attribute of primitive training set, where
ϖ
is number of attribute of primitive
training example set.
Cost coefficient C
= [ C
,
…
, C
Definition 7.16
Primitive training example set E is objective learning task based
set which is not constructed by BSDT algorithm.
Definition 7.17
An algorithm
α
is a decision tree learning algorithm which is
registered in BSDT and certified feasible. The name of the algorithm is its unique
sign. An algorithm set
Α
is a set of all algorithms registered in BSDT.
Case
database
ANA
algorithm
New
introduced
algorithm,
Description
set of case
attributes
ANE algorithm
Classical
case
database
TCBM
algorithm
Optimal
algorithm
CBR
Background
processing
report
Retrieval
information
set
Optimal
algorithm
PPD
algorithm
Primitive
training
example set
Knowledge
database
Training
example
set
Figure 7.8. BSDT algorithm structure
