Using autoencoders as a weight initialization method on deep neural networks for disease detection
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- ISSN
-
1472-6947
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Anmerkungen
-
online resource.
- Erschienen in
-
Using autoencoders as a weight initialization method on deep neural networks for disease detection ; volume:20 ; number:5 ; day:20 ; month:8 ; year:2020 ; pages:1-18 ; date:8.2020
BMC medical informatics and decision making ; 20, Heft 5 (20.8.2020), 1-18, 8.2020
- Urheber
-
Ferreira, Mafalda Falcão
Camacho, Rui
Teixeira, Luís F.
- Beteiligte Personen und Organisationen
-
SpringerLink (Online service)
- DOI
-
10.1186/s12911-020-01150-w
- URN
-
urn:nbn:de:101:1-2020101119291518817074
- Rechteinformation
-
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
14.08.2025, 10:44 MESZ
Datenpartner
Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Ferreira, Mafalda Falcão
- Camacho, Rui
- Teixeira, Luís F.
- SpringerLink (Online service)
Ähnliche Objekte (12)
Improving Neural Language Models with Weight Norm Initialization and Regularization
Distributional initialization of neural networks
Deep recurrent neural network-based autoencoders for acoustic novelty detection
An analysis of weight initialization methods in connection with different activation functions forfeedforward neural networks
Expected Complexity and Gradients of Deep Maxout Neural Networks and Implications to Parameter Initialization
A data-driven approach to neural architecture search initialization
Knowledge injection via ML-based initialization of neural networks
Neural structure fields with application to crystal structure autoencoders
Autoencoders reloaded
Deep learning with autoencoders and LSTM for ENSO forecasting
Ice Sheet Initialization
Salient features for longitudinal patient data using deep recurrent autoencoders
Improving Neural Language Models with Weight Norm Initialization and Regularization
Distributional initialization of neural networks
Deep recurrent neural network-based autoencoders for acoustic novelty detection
An analysis of weight initialization methods in connection with different activation functions forfeedforward neural networks
Expected Complexity and Gradients of Deep Maxout Neural Networks and Implications to Parameter Initialization
A data-driven approach to neural architecture search initialization
Knowledge injection via ML-based initialization of neural networks
Neural structure fields with application to crystal structure autoencoders
Autoencoders reloaded
Deep learning with autoencoders and LSTM for ENSO forecasting
Ice Sheet Initialization
Salient features for longitudinal patient data using deep recurrent autoencoders
Improving Neural Language Models with Weight Norm Initialization and Regularization
Distributional initialization of neural networks
Deep recurrent neural network-based autoencoders for acoustic novelty detection
An analysis of weight initialization methods in connection with different activation functions forfeedforward neural networks
Expected Complexity and Gradients of Deep Maxout Neural Networks and Implications to Parameter Initialization
A data-driven approach to neural architecture search initialization
Knowledge injection via ML-based initialization of neural networks
Neural structure fields with application to crystal structure autoencoders
Autoencoders reloaded
Deep learning with autoencoders and LSTM for ENSO forecasting
Ice Sheet Initialization