抄録
A hybrid fuzzy-neuro classifier that extracts rules in terms of polyhedrons in the input space is proposed. The network uses a fuzzy disjunctive normal form in its hidden layer to effectively map polyhedral regions, which are gradually adjusted during learning, to category labels. The major advantage of the present method lies in that it is quite simple in architecture, every layer enjoys a clear fuzzy logical interpretation, and the number of rules needed is very few. The results of classification experiments seem to be quite promising.
| 元の言語 | English |
|---|---|
| ホスト出版物のタイトル | IEEE International Conference on Fuzzy Systems |
| 出版場所 | Piscataway, NJ, United States |
| 出版者 | IEEE |
| ページ | 577-580 |
| ページ数 | 4 |
| 巻 | 2 |
| 出版物ステータス | Published - 2000 |
| イベント | FUZZ-IEEE 2000: 9th IEEE International Conference on Fuzzy Systems - San Antonio, TX, USA 継続期間: 2000 5 7 → 2000 5 10 |
Other
| Other | FUZZ-IEEE 2000: 9th IEEE International Conference on Fuzzy Systems |
|---|---|
| 市 | San Antonio, TX, USA |
| 期間 | 00/5/7 → 00/5/10 |
Fingerprint
ASJC Scopus subject areas
- Chemical Health and Safety
- Software
- Safety, Risk, Reliability and Quality
これを引用
Adaptive arrangement classifier via neuro-fuzzy modeling. / Shiina, Kempei.
IEEE International Conference on Fuzzy Systems. 巻 2 Piscataway, NJ, United States : IEEE, 2000. p. 577-580.研究成果: Conference contribution
}
TY - GEN
T1 - Adaptive arrangement classifier via neuro-fuzzy modeling
AU - Shiina, Kempei
PY - 2000
Y1 - 2000
N2 - A hybrid fuzzy-neuro classifier that extracts rules in terms of polyhedrons in the input space is proposed. The network uses a fuzzy disjunctive normal form in its hidden layer to effectively map polyhedral regions, which are gradually adjusted during learning, to category labels. The major advantage of the present method lies in that it is quite simple in architecture, every layer enjoys a clear fuzzy logical interpretation, and the number of rules needed is very few. The results of classification experiments seem to be quite promising.
AB - A hybrid fuzzy-neuro classifier that extracts rules in terms of polyhedrons in the input space is proposed. The network uses a fuzzy disjunctive normal form in its hidden layer to effectively map polyhedral regions, which are gradually adjusted during learning, to category labels. The major advantage of the present method lies in that it is quite simple in architecture, every layer enjoys a clear fuzzy logical interpretation, and the number of rules needed is very few. The results of classification experiments seem to be quite promising.
UR - http://www.scopus.com/inward/record.url?scp=0033686199&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033686199&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0033686199
VL - 2
SP - 577
EP - 580
BT - IEEE International Conference on Fuzzy Systems
PB - IEEE
CY - Piscataway, NJ, United States
ER -