File:Hinton Salakhutdinov 2006 Fig1.png
Hinton_Salakhutdinov_2006_Fig1.png (707 × 562 pixels, file size: 104 KB, MIME type: image/png)
Fig. 1. Pretraining consists of learning a stack of restricted Boltzmann machines (RBMs), each having only one layer of feature detectors. The learned feature activations of one RBM are used as the ‘‘data’’ for training the next RBM in the stack. After the pretraining, the RBMs are ‘‘unrolled’’ to create a deep autoencoder, which is then fine-tuned using backpropagation of error derivatives. In: Geoffrey E. Hinton, and R. R. Salakhutdinov (2006). Reducing the dimensionality of data with neural networks. Science, 313:504-507. [ https://doi.org/10.1126/science.1127647 DOI: 10.1126/science.1127647]
File history
Click on a date/time to view the file as it appeared at that time.
Date/Time | Thumbnail | Dimensions | User | Comment | |
---|---|---|---|---|---|
current | 21:06, 12 August 2018 | 707 × 562 (104 KB) | Omoreira (talk | contribs) | <B>Fig. 1.</B> Pretraining consists of learning a stack of restricted Boltzmann machines (RBMs), each having only one layer of feature detectors. The learned feature activations of one RBM are used as the ‘‘[[da... |
You cannot overwrite this file.
File usage
The following page uses this file: