TY  - RPRT
U1  - Arbeitspapier
A1  - Bahdanau, Dzmitry
A1  - Jaeger, Herbert
T1  - Smart Decisions by Small Adjustments: Iterating Denoising Autoencoders
N2  - An iterative neural architecture based on repeated application of the Denoising Autoencoder is introduced. The architecture is placed in the family of other approaches involving networks of simple units and iteration at the exploitation stage. It is shown that repeated feeding of a pattern to a Denoising Autoencoder often yields non-trivial sensible improvements of the pattern. This statement is supported by a classification experiment, in which the data transformed by our architecture is shown to be more linearly separable than the original samples.
AB  - An iterative neural architecture based on repeated application of the Denoising Autoencoder is introduced. The architecture is placed in the family of other approaches involving networks of simple units and iteration at the exploitation stage. It is shown that repeated feeding of a pattern to a Denoising Autoencoder often yields non-trivial sensible improvements of the pattern. This statement is supported by a classification experiment, in which the data transformed by our architecture is shown to be more linearly separable than the original samples.
T3  - Constructor University Technical Reports - 32 
Y1  - 2014
U6  - https://nbn-resolving.org/urn:nbn:de:gbv:579-opus-1006885
UN  - https://nbn-resolving.org/urn:nbn:de:gbv:579-opus-1006885
ER  -