Databases Reference
In-Depth Information
TABLE 8.2: DHGN Subnet Associative Array Structure after Subpatterns
00001 and 11111 Have Been Memorized
Bias Array
Index
GN ID
Row
Layer
Value
Entry
1
1
0
0
1
#,1
2
1
0
0
1
1,1
3
1
0
0
1
1,1
4
1
0
0
1
1,2
5
1
0
0
-
-
6
2
0
1
1
#,2
7
2
0
1
1
2,2
8
2
0
1
1
2,2
9
2
0
1
1
2,2
1
1,#
10
2
0
1
2
2,#
11
1
1
#
1
#,1,1
12
1
1
#
1
1,1,1
13
1
1
#
1
1,1,#
14
2
1
#
1
#,1,1
15
2
1
#
1
1,1,1
16
2
1
#
1
1,1,#
17
1
2
#
1
1
18
2
2
#
1
2
ing large-scale data analyses. A framework proposed by Muhamad Amin
and Khan [55] employs a grid-enabled DHGN distributed pattern recogni-
tion scheme. The framework comprises a commodity-grid (CoG) network
[74] for pattern recognition implementation using the DHGN approach. The
commodity-grid provides an easy-to-use front-end for accessing a distributed
system supporting complex operations.
The proposed framework for our distributed pattern recognition is a com-
bination of a commodity-grid based architecture and the single-cycle learning
DHGN associative memory approach for pattern recognition. The commodity
grid infrastructure enables us to offer the pattern recognition service to multi-
ple users from different expertise domains and application areas. For instance,
climatic change research can use the proposed system for long-term climate
pattern discovery, while the bioinformatics field can use this resource for pro-
tein structure recognition and classification. This extends the scalability of
the DHGN DPR scheme across different application domains.
