Transcription of A fast learning algorithm for deep belief nets
{{id}} {{{paragraph}}}
Example: confidence
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 enactivitieswhengivenadat
2. The learning algorithm is unsupervised but can be ap-plied to labeled data by learning a model that generates both the label and the data. 3. There is a fine-tuning algorithm that learns an excel-lent generative model which outperforms discrimina-tive methods on the MNIST database of hand-written digits. 4.
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: