Autoencoder: Difference between revisions

Revision as of 01:58, 23 November 2007

Revision as of 02:04, 23 November 2007

Line 15:

== Training ==

An auto-encoder is often trained using one of the many backpropagation[[Backpropagation]] variants ([[Conjugate Gradient Method]], [[Steepest DescenDescent]], etc.)

A technique developed Geoffrey Hinton for training many-layered "deep" auto-encoders involves treating each set of two layers like a [[Boltzmann_machine#Restricted_Boltzmann_Machine|Restricted Boltzmann Machine]] for pre-training to approximate a good solution and then using a backpropagation technique to fine-tune.

Line 26:

{{compu-AI-stub}}

<s>Strike-through text</s>