Information Technology Reference
In-Depth Information
1
0.9
Normal
REA
SMOTE
0.8
0.7
SERA
0.6
UB
0.5
0.4
10
20
30
40
50
60
70
80
90
100
(a) OA of algorithms in comparison
for SHP dataset under setup 2
1
0.9
SERA
UB
REA
0.8
0.7
0.6
Normal
0.5
SMOTE
0.4
10
20
30
40
50
60
70
80
90
100
(b) AUC of algorithms in comparison
for SHP dataset under setup 2
Figure 7.11 OA and AUROC for SHP dataset under setup 2 .
training data chunk or already have a mechanism to obsolete the old hypotheses,
such as Learn ++ .
Imagine the hypotheses set H defined in Algorithm 7.4, which is a first-in-
first-out (FIFO) queue. The original design of REA physically sets the capacity
of H to be infinity, as from the time of its creation, any hypothesis will stay in
memory until the end of the data stream. Now let us assume that H has a smaller
capacity. Should the number of stored hypotheses exceed the capacity of H ,the
oldest hypothesis would automatically be removed from H . In this way, it can
Search WWH ::




Custom Search