PMID- 16121740
OWN - NLM
STAT- MEDLINE
DCOM- 20050916
LR  - 20191210
IS  - 1045-9227 (Print)
IS  - 1045-9227 (Linking)
VI  - 16
IP  - 4
DP  - 2005 Jul
TI  - Improvement of the neighborhood based Levenberg-Marquardt algorithm by local 
      adaptation of the learning coefficient.
PG  - 988-92
AB  - In this letter, an improvement of the recently developed neighborhood-based 
      Levenberg-Marquardt (NBLM) algorithm is proposed and tested for neural network 
      (NN) training. The algorithm is modified by allowing local adaptation of a 
      different learning coefficient for each neighborhood. This simple add-in to the 
      NBLM training method significantly increases the efficiency of the training 
      episodes carried out with small neighborhood sizes, thus, allowing important 
      savings in memory occupation and computational time while obtaining better 
      performance than the original Levenberg-Marquardt (LM) and NBLM methods.
FAU - Toledo, A
AU  - Toledo A
FAU - Pinzolas, M
AU  - Pinzolas M
FAU - Ibarrola, J J
AU  - Ibarrola JJ
FAU - Lera, G
AU  - Lera G
LA  - eng
PT  - Comparative Study
PT  - Evaluation Study
PT  - Letter
PT  - Research Support, Non-U.S. Gov't
PL  - United States
TA  - IEEE Trans Neural Netw
JT  - IEEE transactions on neural networks
JID - 101211035
SB  - IM
MH  - *Algorithms
MH  - Computer Simulation
MH  - *Models, Statistical
MH  - *Neural Networks, Computer
EDAT- 2005/08/27 09:00
MHDA- 2005/09/17 09:00
CRDT- 2005/08/27 09:00
PHST- 2005/08/27 09:00 [pubmed]
PHST- 2005/09/17 09:00 [medline]
PHST- 2005/08/27 09:00 [entrez]
AID - 10.1109/TNN.2005.849849 [doi]
PST - ppublish
SO  - IEEE Trans Neural Netw. 2005 Jul;16(4):988-92. doi: 10.1109/TNN.2005.849849.