aneuralcomputingbasedclaificationruleminingframeworknamedneucrumisproposedandsuccefullyaliedtotyphoonforecastingdomain.
thirdly,ageneticalgorithmbasedselectiveneuralnetworkeemblearoachnamedgasenisproposed.experimentalresultsshowthatgasenoutperformspopulareemblearoachesatpresent.then,aviewecificeemblearoachnamedvsisdevelopedtoalyneuralnetworkeembletoviewinvariantfacerecognition,whichhastheabilityofperforminghighqualityrecognitionwithoutviewpre-estimation.moreover,bothanoveloutput-combiningmethodandauniquetwo-layer-eemblearchitecturearedesigned,sothatneuralnetworkeembleisembeddedinthelungcancerearlystagediagnosissystemlcdstoperformlungcancercellidentification,whichgreatlylowerstherateofmiedidentificationoflungcancercells.
fourthly,ageneticalgorithmbasedaroachnamedefanetthatevolvesfault-tolerantneuralnetworksforsingle-nodeopenfaultisproposed.experimentalresultsshowthatefanetcanevolveneuralnetworkswithbothrobustfault-tolerantabilityandstronggeneralizationabilitywhilekeepingtheindependenceamongnet
worktopology,trainingalgorithm,andfault-tolerantproceing.besides,athree-phrasearoachnamedt3isproposedformulti-nodeopenfault,whichhasbeenaliedtofac.experimentalresultsshowthatt3cantradeoffthefault-tolerantabilityandstructuralcomplexityoftheneuralnetwork.
fifthly,ahybriddecisiontreearoachnamedhdtthatcombinesdecisiontreeandfeedforwardneuralnetworksisproposed,whosetreegrowingalgorithmandneuralproceingmechanismareprimarilydescribed.then,incrementallearningandcotructiveinduc