Transcription of A fast learning algorithm for deep belief nets
{{id}} {{{paragraph}}}
A fastlearningalgorithmfordeepbeliefnets TehDepartmentofComputerScienceNationalUn iversityofSingapore3 ScienceDrive 3, showhowtouse complementarypriors toeliminatetheexplainingawayeffectsthatm akeinferencedifficultindensely-connected beliefnetsthathave many ,wederive a fast,greedyalgo-rithmthatcanlearndeep,di rectedbeliefnetworksonelayerata time,providedthetoptwo lay-ersformanundirectedassociative memory. Thefast,greedyalgorithmis usedto initializea slowerlearningprocedurethatfine-tunesthe weightsus-inga contrastive ,a networkwiththreehiddenlayersformsa verygoodgenerative modelgivesbetterdigitclassificationthant hebestdiscrimi-native associative memoryandit is easytoex-ploretheseravinesbyusingthedire ctedconnec-tionstodisplaywhattheassociat ive difficultin densely-connected,directedbeliefnetsthat have many hiddenlayersbecauseit is difficultto infertheconditionaldistributionofthehidd enactivitieswhengivenadatavector.
A fast learning algorithm for deep belief nets Geoffrey E. Hinton and Simon Osindero Department of Computer Science University of Toronto 10 Kings College Road
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}