A recursive algorithm for fuzzy Min-Max networks

被引：20

作者：

Rizzi, A ^{[1
]}

Panella, M ^{[1
]}

Mascioli, FMF ^{[1
]}

Martinelli, G ^{[1
]}

机构：

[1] Univ Roma La Sapienza, INFO COM Dpt, I-00184 Rome, Italy

来源：

IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL VI | 2000年

关键词：

classification; constructive algorithms; Min-Max networks; ARC;

D O I：

10.1109/IJCNN.2000.859451

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In the present paper, a new algorithm to train Min-Max neural models is proposed. It is based on the ARC technique, which overcomes some undesired properties of the original Simpson's algorithm. In particular, training results do not depend on pattern presentation order and hyperbox expansion is not limited by a fixed maximum size, so that it is possible to have different covering resolutions. ARC generates the optimal Min-Mar network by a succession of hyperbox cuts. The generalization capability of ARC technique depends mostly on the adopted cutting strategy. A new recursive cutting procedure allows ARC technique to yield a better performance. Some real data benchmarks are considered for illustration.

引用

页码：541 / 546

页数：6

共 10 条

[1]

Anderson E., 1935, Bulletin of the American IRIS Society, V59, P2

[2]

COSTANTINI G, 1999, P ECMCS 99 KRAK POL

[3]

COSTANTINI G, 1999, P JIM 99 ISSY LES MO, P51

[4] On neurobiological, neuro-fuzzy, machine learning, and statistical pattern recognition techniques [J].

Joshi, A ;

Ramakrishman, N ;

Houstis, EN ;

Rice, JR .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (01) :18-31

[5]

MASCIOLI FMF, 1997, P ICASSP 97 MUN GERM, V4, P3193

[6]

PRECHELT L, PROBEN 1 SET NEURAL

[7]

Rizzi A, 1998, 1998 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AT THE IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE - PROCEEDINGS, VOL 1-2, P1435, DOI 10.1109/FUZZY.1998.686330

[8]

Simpson P. K., 1993, IEEE Transactions on Fuzzy Systems, V1, P32, DOI 10.1109/TFUZZ.1993.390282

[9] FUZZY MIN MAX NEURAL NETWORKS .1. CLASSIFICATION [J].

SIMPSON, PK .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (05) :776-786

[10]

Suh IH, 1999, IEEE T FUZZY SYST, V7, P271, DOI 10.1109/91.771084

← 1 →