Produkt
KlappentextIn 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.
Details
ISBN/GTIN978-3-95908-648-6
ProduktartBuch
EinbandartGebunden
Verlag
Erscheinungsjahr2024
Erscheinungsdatum15.02.2024
Seiten196 Seiten
SpracheEnglisch
MasseBreite 170 mm, Höhe 240 mm, Dicke 16 mm
Gewicht435 g
Artikel-Nr.55907466
Rubriken