LSTM Recurrent Neural Networks for Signature Verification - Tiflin, Conrad
35,99 €
inkl. MwSt.
Versandkostenfrei*
Versandfertig in 1-2 Wochen
payback
18 °P sammeln
  • Broschiertes Buch

The author investigated the application of Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) to the task of signature verification. Traditional RNNs are capable of modeling dynamical systems with hidden states; they have been successfully applied to domains ranging from financial forecasting to control and speech recognition. This manuscript is the result of successfully applying on-line signature time series data to traditional LSTM, LSTM with forget gates and LSTM with peephole connections algorithms originally developed by S. Hochreiter and J. Schmidhuber. It can be clearly…mehr

Andere Kunden interessierten sich auch für
Produktbeschreibung
The author investigated the application of Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) to the task of signature verification. Traditional RNNs are capable of modeling dynamical systems with hidden states; they have been successfully applied to domains ranging from financial forecasting to control and speech recognition. This manuscript is the result of successfully applying on-line signature time series data to traditional LSTM, LSTM with forget gates and LSTM with peephole connections algorithms originally developed by S. Hochreiter and J. Schmidhuber. It can be clearly seen in this pattern classification problem that traditional LSTM RNNs outperform LSTMs with forget gates and peephole connections. The latter also outperform traditional RNNs which cannot seem to even learn this task due to the long-term dependency problem.
Hinweis: Dieser Artikel kann nur an eine deutsche Lieferadresse ausgeliefert werden.
Autorenporträt
Conrad completed his Masters Degree with Cum Laude with the Intelligent Systems Group of the Department of Computer Science at the University of the Western Cape. His research interests span Recurrent Neural Networks (RNNs) and their applications to time series prediction as well as the application thereof to Biometric technologies.