PMID- 18244382
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20100628
LR  - 20161020
IS  - 1045-9227 (Print)
IS  - 1045-9227 (Linking)
VI  - 12
IP  - 2
DP  - 2001
TI  - Divide-and-conquer learning and modular perceptron networks.
PG  - 250-63
LID - 10.1109/72.914522 [doi]
AB  - A novel modular perceptron network (MPN) and divide-and-conquer learning (DCL) 
      schemes for the design of modular neural networks are proposed. When a training 
      process in a multilayer perceptron falls into a local minimum or stalls in a flat 
      region, the proposed DCL scheme is applied to divide the current training data 
      region into two easier to be learned regions. The learning process continues when 
      a self-growing perceptron network and its initial weight estimation are 
      constructed for one of the newly partitioned regions. Another partitioned region 
      will resume the training process on the original perceptron network. Data region 
      partitioning, weight estimating and learning are iteratively repeated until all 
      the training data are completely learned by the MPN. We evaluated and compared 
      the proposed MPN with several representative neural networks on the two-spirals 
      problem and real-world dataset. The MPN achieved better weight learning 
      performance by requiring much less data presentations during the network training 
      phases, and better generalization performance, and less processing time during 
      the retrieving phase.
FAU - Fu, H C
AU  - Fu HC
AD  - Department of Computer Science and Information Engineering, National Chiao Tung 
      University, Hsinchu, Taiwan 300, R.O.C.
FAU - Lee, Y P
AU  - Lee YP
FAU - Chiang, C C
AU  - Chiang CC
FAU - Pao, H T
AU  - Pao HT
LA  - eng
PT  - Journal Article
PL  - United States
TA  - IEEE Trans Neural Netw
JT  - IEEE transactions on neural networks
JID - 101211035
EDAT- 2008/02/05 09:00
MHDA- 2008/02/05 09:01
CRDT- 2008/02/05 09:00
PHST- 2008/02/05 09:00 [pubmed]
PHST- 2008/02/05 09:01 [medline]
PHST- 2008/02/05 09:00 [entrez]
AID - 10.1109/72.914522 [doi]
PST - ppublish
SO  - IEEE Trans Neural Netw. 2001;12(2):250-63. doi: 10.1109/72.914522.