Smart Decisions by Small Adjustments: Iterating Denoising Autoencoders
- 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.
Download full text files
| Author: | Dzmitry Bahdanau, Herbert Jaeger |
|---|---|
| URN: | urn:nbn:de:gbv:579-opus-1006885 |
| Series (Serial Number): | Constructor University Technical Reports (32) |
| Document Type: | Technical Report |
| Language: | English |
| Date of first Publication: | 2014/05/01 |
| Publishing Institution: | IRC-Library, Information Resource Center der Jacobs University Bremen |
| Release Date: | 2017/01/03 |
| Schools (for defense dates until 2014): | SES School of Engineering and Science |
| loc: | Q Science / QA Mathematics (incl. computer science) / QA71-90 Instruments and machines / QA75.5-76.95 Electronic computers. Computer science / QA76.87 Neural computers. Neural networks |
