• Sie verwenden einen veralteten Webbrowser, weshalb es zu Problemen mit der Darstellung kommen kann. Bei Problemen mit der Bestellabgabe können Sie gerne auch telefonisch bestellen unter: 01805 / 30 99 99 (0,14 €/Min., Mobil max. 0,42 €/Min.)

Auto- Encoder

Auto- Encoder
Autor: Lambert M. Surhone / Mariam T. Tennoe / Susan F. Henssonow
Verfügbarkeit: Auf Lager.
Artikelnummer: 700532
ISBN / EAN: 9786131368707

Verfügbarkeit: sofort lieferbar

34,00 €
Inkl. MwSt. , zzgl. Versandkosten



Please note that the content of this book primarily consists of articles available from Wikipedia or other free sources online. An auto-encoder is an artificial neural network used for learning efficient codings. The aim of an auto-encoder is to learn a compressed representation (encoding) for a set of data. This means it is being used for dimensionality reduction. More specifically, it is a feature extraction method.An auto-encoder is often trained using one of the many backpropagation variants (conjugate gradient method, steepest descent, etc.) Though often reasonably effective, there are fundamental problems with using backpropagation to train networks with many hidden layers. Once the errors get backpropagated to the first few layers, they are minuscule, and quite ineffectual. This causes the network to almost always learn to reconstruct the average of all the training data. Though more advanced backpropagation methods (such as the conjugate gradient method) help with this to some degree, it still results in very slow learning and poor solutions. This problem is remedied by using initial weights that approximate the final solution. The process to find these initial weights is often called pretraining.

0 Kundenmeinungen

Bitte schreiben Sie uns Ihre Meinung zu: Auto- Encoder

  • Wenn Sie dieses Eingabefeld sehen sollten, lassen Sie es leer!

Sie könnten auch an folgenden Produkten interessiert sein