Learning momentum constant neuron monte carlo search
412 |
|
mutation |
|
---|---|---|---|
|
|||
|
McCulloch and Pitts neuron model 167–70
5, 169 neural expert system 262–8
triangle 93–4, 116–17, 271 evolutionary 285–7
membership value, see degree of feedback 188–9
WHEN NEEDED 133, 142, 146 defuzzification layer 273
Mexican hat function 206–7 fuzzification layer 269
momentum constant 185–6 neuron 166–8
Monte Carlo search 14, 245 artificial 168
output layer 175
convergence 183
learning 179–80
accelerated learning 185–8 multiple antecedents 26, 77, 105 multiple consequents 27, 105NP-complete problem 8, 235 NP-hard problem 336
normalisation layer 279
normalised firing strength 279 numerical object 27multi-valued logic 89
object-oriented programming 132
odds 67–8 | INDEX | 413 | |||
---|---|---|---|---|---|
|
|||||
offspring chromosome, see child |
|
||||
one-parent inheritence 138–40 | |||||
operational database | procedure |
|
|||
operations of fuzzy sets 98–100 |
|
||||
|
|
||||
OPS 11, 30, 310 | |||||
optical character recognition |
|
||||
|
|||||
optimisation 303, 336–9 |
ordered crossover | Q | |
---|---|---|
output layer 175 | query tool 351 |
output membership layer 272–3
overfitting 325 R
parent chromosome 222–3 goal-driven 38–40
parent node 352 symbolic 34
probabilistic OR 109, 273
rule table, see fuzzy rule table