Intelligent system for automatic feature detection and selection or identification
- Pao-Shan Shiang, TW
- Framingham, MA
- San Francisco, CA
A neural network uses a fuzzy membership function, the parameters of which are adaptive during the training process, to parameterize the interconnection weights between an (n-1)'th layer and an n'th layer of the network. Each j'th node in each k'th layer of the network except the input layer produces its output value y.sub.k,j according to the function ##EQU1## where N.sub.k-1 is the number of nodes in layer k-1, i indexes the nodes of layer k-1 and all the w.sub.k,i,j are interconnection weights. The interconnection weights to all nodes j in the n'th layer are given by w.sub.n,i,j =w.sub.n,j (i, p.sub.n,j,1, . . . , p.sub.n,j,p.sbsb.n). The apparatus is trained by setting values for at least one of the parameters p.sub.n,j,1, . . . , p.sub.n,j,Pn. Preferably the number of parameters P.sub.n is less than the number of nodes N.sub.n-1 in layer n-1. w.sub.n,j (i,p.sub.n,j,1, . . . , p.sub.n,j,Pn) can be convex in i, and it can be bell-shaped. Sample functions for w.sub.n,j (i, p.sub.n,j,1, . . . , p.sub.n,j,Pn) include ##EQU2##
- Research Organization:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- DOE Contract Number:
- W-7405-ENG-48
- Assignee:
- United States of America as represented by United States (Washington, DC)
- Patent Number(s):
- US 5664066
- OSTI ID:
- 871136
- Country of Publication:
- United States
- Language:
- English
Similar Records
Application of Selected Artificial Intelligence Methods in a System Predicting the Microstructure of Compacted Graphite Iron
Short term daily average and peak load predications using a hybrid intelligent approach
Related Subjects
automatic
feature
detection
selection
identification
neural
network
fuzzy
membership
function
parameters
adaptive
training
process
parameterize
interconnection
weights
n-1
layer
node
input
produces
output
value
according
equ1
k-1
nodes
indexes
sbsb
apparatus
trained
setting
values
pn
preferably
convex
bell-shaped
sample
functions
equ2
neural network
training process
feature detection
neural net
output value
/706/