Transcription of A fast learning algorithm for deep belief nets
{{id}} {{{paragraph}}}
Example: stock market
A fast learning algorithm for deep belief nets
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.
image 10 label units This could be the top level of another sensory pathway Figure 1: The network used to model the joint distribution of digit images and digit labels. In this paper, each training case consists of an image and an explicit class label, but work in progress has shown that the same learning algorithm can
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: