Page 131 - Artificial Intelligence in the Age of Neural Networks and Brain Computing

120 CHAPTER 6 Evolving and Spiking Connectionist Systems

• SOFMLS: online self-organizing fuzzy modified least-squares network [58];
• Online sequential extreme learning machine [59];
• Finding features for real-time premature ventricular contraction detection using a
fuzzy neural network system [60];
• Evolving fuzzy ruleebased classifiers [61];
• A novel generic Hebbian ordering-based fuzzy rule base reduction approach to
Mamdani neurofuzzy system [62];
• Implementation of fuzzy cognitive maps based on fuzzy neural network and
application in prediction of time-series [63];
• Backpropagation to train an evolving radial basis function neural network [64];
• Smooth transition autoregressive models and fuzzy ruleebased systems: func-
tional equivalence and consequences [65];
• Development of an adaptive neurofuzzy classifier using linguistic hedges [66];
• A metacognitive sequential learning algorithm for neurofuzzy inference system
[67];
• Metacognitive RBF network and its projection-based learning algorithm for
classification problems [68];
• SaFIN: a self-adaptive fuzzy inference network [69];
• A sequential learning algorithm for metacognitive neurofuzzy inference system
for classification problems [70];
• Architecture for development of adaptive online prediction models [71];
• Clustering and coevolution to construct neural network ensembles: an experi-
mental study [72];
• Algorithms for real-time clustering and generation of rules from data [73];
• SAKM: self-adaptive kernel machineda kernel-based algorithm for online
clustering [74];
• A BCM theory of metaplasticity for online self-reorganizing fuzzy-associative
learning [75];
• Evolutionary strategies and genetic algorithms for dynamic parameter optimi-
zation of evolving fuzzy neural networks [76];
• Incremental learning and model selection for radial basis function network
through sleep learning [77];
• Interval-based evolving modeling [78];
• Evolving granular classification neural networks [79];
• Stability analysis for an online evolving neurofuzzy recurrent network [80];
• A TSK fuzzy inference algorithm for online identification [81];
• Design of experiments in neurofuzzy systems [82];
• EFuNNs ensemble construction using a clustering method and a coevolutionary
genetic algorithm [83];
• eT2FIS: an evolving type-2 neural fuzzy inference system [84];
• Designing radial basis function networks for classification using differential
evolution [85];
• A metacognitive neurofuzzy inference system (McFIS) for sequential classifi-
cation problems [86];