Development and Analysis of non-standard Echo State Networks
(Sprache: Englisch)
In an era of complex deep learning architectures like transformers, CNNs, and LSTM cells, the challenge persists: the hunger for labeled data and high energy. This dissertation explores Echo State Network (ESN), an RNN variant. ESN's efficiency in linear...
Leider schon ausverkauft
Buch (Gebunden)
- Lastschrift, Kreditkarte, Paypal, Rechnung
- Kostenlose Rücksendung
Produktdetails
Produktinformationen zu „Development and Analysis of non-standard Echo State Networks “
Klappentext zu „Development and Analysis of non-standard Echo State Networks “
In an era of complex deep learning architectures like transformers, CNNs, and LSTM cells, the challenge persists: the hunger for labeled data and high energy. This dissertation explores Echo State Network (ESN), an RNN variant. ESN's efficiency in linear regression training and simplicity suggest pathways to resource-efficient, adaptable deep learning. Systematically deconstructing ESN architecture into flexible modules, it introduces basic ESN models with random weights and efficient deterministic ESN models as baselines. Diverse unsupervised pre-training methods for ESN components are evaluated against these baselines. Rigorous benchmarking across datasets - time-series classification, audio recognition - shows competitive performance of ESN models with state-of-the-art approaches. Identified nuanced use cases guiding model preferences and limitations in training methods highlight the importance of proposed ESN models in bridging reservoir computing and deep learning.
Bibliographische Angaben
- Autor: Peter Steiner
- 2024, 196 Seiten, Maße: 17 x 24 cm, Gebunden, Englisch
- Verlag: TUDpress
- ISBN-10: 3959086482
- ISBN-13: 9783959086486
- Erscheinungsdatum: 15.02.2024
Sprache:
Englisch
Kommentar zu "Development and Analysis of non-standard Echo State Networks"
Schreiben Sie einen Kommentar zu "Development and Analysis of non-standard Echo State Networks".
Kommentar verfassen