Network structure formation in thermally-induced gelation of glycinin

1984 ◽  
Vol 32 (2) ◽  
pp. 349-352 ◽  
Author(s):  
Takashi Nakamura ◽  
Shigeru Utsumi ◽  
Tomohiko Mori
Keyword(s):  
Structure Formation ◽  
Network Structure ◽  
Thermally Induced

Processes of Silica Network Structure Formation in Reverse Micellar Systems

Langmuir ◽  
2001 ◽  
Vol 17 (14) ◽  
pp. 4189-4195 ◽  
Author(s):  
Makoto Harada ◽  
Shintaro Itakura ◽  
Akihisa Shioi ◽  
Motonari Adachi
Keyword(s):  
Structure Formation ◽  
Network Structure ◽  
Silica Network ◽  
Micellar Systems ◽  
Reverse Micellar Systems ◽  
Reverse Micellar

THERMALLY INDUCED STRUCTURE FORMATION IN POLYETHYLENE SOLUTIONS

1992 ◽  
pp. 501
Author(s):  
L. AERTS ◽  
H. BERGHMANS ◽  
P. MOLDENAERS ◽  
J. MEWIS ◽  
M. KUNZ
Keyword(s):  
Structure Formation ◽  
Thermally Induced ◽  
Induced Structure

Studies on Effects of Initialization on Structure Formationand Generalization of Structural Learning with Forgetting

2004 ◽  
Vol 8 (6) ◽  
pp. 621-626 ◽  
Author(s):  
Hiroshi Shiratsuchi ◽  
◽  
Hiromu Gotanda ◽  
Katsuhiro Inoue ◽  
Kousuke Kumamaru ◽  
...  
Keyword(s):  
Neural Networks ◽  
Structure Formation ◽  
Network Structure ◽  
Center Of Gravity ◽  
Input Pattern ◽  
Structural Learning ◽  
Generalization Ability ◽  
Multilayer Neural Networks ◽  
Pass Through

In this paper, our proposed initialization for multilayer neural networks (NN) applies to the structural learning with forgetting. Initialization consists of two steps: weights of hidden units are initialized so that their hyperplanes pass through the center of gravity of an input pattern set, and weights of output units are initialized to zero. Several simulations were performed to study how the initialization effects the structure formation of the NN. From the simulation result, it was confirmed that the initialization gives better network structure and higher generalization ability.

Sign in / Sign up

Export Citation Format

Share Document