Why Does Unsupervised Pre-training Help Deep Learning?

Source: jmlr.org
Type: PDF Document
Parse: pending
Tags:

The increase in error variance and mean for deeper architectures without pre-training suggests that increasing depth increases the probability of finding poor ...

Tips: If the preview is unavailable, open the Source PDF directly from the publisher's website. Preview availability depends on the publisher's settings, and some documents may restrict third-party iframe preview.