Introduction
Soyouwanttolearnaboutdeeplearningandneuralnetworks,butyoudon’thaveaclue
whatmachinelearningevenis.Thisbookisforyou.
Perhapsyou’vealreadytriedtoreadsometutorialsaboutdeeplearning,andwerejustleft
scratchingyourheadbecauseyoudidnotunderstandanyofit.Thisbookisforyou.
Believe the hype. Deep learning is making waves. At the time of this writing (March
2016),Google’sAlghaGoprogramjustbeat9-danprofessionalGoplayerLeeSedolatthe
gameofGo,aChineseboardgame.
Experts in the field of Artificial Intelligence thought we were 10 years away from
achieving a victory against a top professional Go player, but progress seems to have
accelerated!
While deep learning is a complex subject, it is not any more difficulttolearnthanany
othermachinelearningalgorithm.Iwrotethisbooktointroduceyoutotheprerequisites
ofneuralnetworks,sothatlearningaboutneuralnetworksinthefuturewillseemlikea
naturalextensionofthesetopics.Youwill getalongfinewithundergraduate-levelmath
andprogrammingskill.
Allthematerialsinthisbookcanbedownloadedandinstalledforfree.Wewillusethe
Pythonprogramminglanguage,alongwiththenumericalcomputinglibraryNumpy.
Unlikeothermachinelearningalgorithms,deeplearningisparticularlypowerfulbecause
itautomaticallylearnsfeatures.Thatmeansyoudon’tneedtospendyourtimetryingto
comeupwithandtest“kernels”or“interactioneffects”-somethingonlystatisticianslove
to do.Instead,we will eventually let theneuralnetwork learn these things forus.Each
layeroftheneuralnetworkismadeupoflogisticregressionunits.
Doyouwantagentleintroductiontothis“darkart”,withpracticalcodeexamplesthatyou
cantryrightawayandapplytoyourowndata?Thenthisbookisforyou.
Thisbookwasdesignedtocontainalltheprerequisiteinformationyouneedformynext
book,DeepLearninginPython:MasterDataScienceandMachineLearningwithModern
NeuralNetworkswritteninPython,Theano,andTensorFlow.
评论0