Deep learning for time series. Attention-based models. 13.1 - Introduction/ClipID:40426 previous clip next clip

Keywords: deep learning machine learning time series
Recording date 2022-01-25

Course

Machine Learning for Time Series

Lecturer

Dario Zanca

Via

IdM-login / Studon

Language

English

Organisational Unit

Friedrich-Alexander-Universität Erlangen-Nürnberg

Producer

Friedrich-Alexander-Universität Erlangen-Nürnberg

Recap of RNNs (and derivates) limitations, and introduction to today's topics: attention models and the Transformer architecture.

Up next in Chapter

Deep learning for time series. Attention-based models. 13.2 - Attention models
Schloss1
Dario Zanca
2022-01-25
IdM-login / Studon
Deep learning for time series. Attention-based models. 13.3 - The Transformer architecture
Schloss1
Dario Zanca
2022-01-25
IdM-login / Studon
Deep learning for time series. Attention-based models. 13.4 - Recap and insights
Schloss1
Dario Zanca
2022-01-25
IdM-login / Studon
Domain adaptation. 14.1 - Transfer Learning and Domain Adaptation
Schloss1
Dr. Luis Ignacio Lopera Gonzalez
2022-02-01
IdM-login / Studon
Domain adaptation. 14.2 - Homogeneous Domain Adaptation
Schloss1
Dr. Luis Ignacio Lopera Gonzalez
2022-02-01
IdM-login / Studon

More clips in this category "Friedrich-Alexander-Universität Erlangen-Nürnberg"

Vertiefung Diagnoseprozess
2022-05-18
Studon
protected  
Blatt 4
2022-05-18
Studon
protected  
Vorlesung 09 - Hauptachsentransformation
2022-05-18
Passwort
protected  
KRMT: Logic-based knowldege representation for mathematic/technical knowledge
2022-05-18
IdM-login
protected  
Speech and Language Understanding (SLU)
2022-05-17
IdM-login
protected  
Speech and Language Understanding (SLU)
2022-05-17
IdM-login
protected