Publication: Biologically-Inspired Continual Learning of Human Motion Sequences
Biologically-Inspired Continual Learning of Human Motion Sequences
Date
Date
Date
Citations
Ott, J., & Liu, S.-C. (2023). Biologically-Inspired Continual Learning of Human Motion Sequences. online. https://doi.org/10.1109/icassp49357.2023.10095490
Abstract
Abstract
Abstract
This work proposes a model for continual learning on tasks involving temporal sequences, specifically, human motions. It improves on a recently proposed brain-inspired replay model (BI-R) by building a biologically-inspired conditional temporal variational autoencoder (BI-CTVAE), which instantiates a latent mixture-of-Gaussians for class representation. We investigate a novel continual-learning-to-generate (CL2Gen) scenario where the model generates motion sequences of different classes. The generative accuracy of the model is tested
Metrics
Downloads
Views
Citations
Additional indexing
Creators (Authors)
- Ott, Joachim
- Liu, Shih-Chii
Event Title
Event Title
Event Title
Event Location
Event Location
Event Location
Event Country
Event Country
Event Country
Event Start Date
Event Start Date
Event Start Date
Event End Date
Event End Date
Event End Date
Page range/Item number
Page range/Item number
Page range/Item number
Item Type
Item Type
Item Type
In collections
Language
Language
Language
Date available
Date available
Date available
Series Name
Series Name
Series Name
ISSN or e-ISSN
ISSN or e-ISSN
ISSN or e-ISSN
ISBN or e-ISBN
ISBN or e-ISBN
ISBN or e-ISBN
OA Status
OA Status
OA Status
Publisher DOI
Metrics
Downloads
Views
Citations
Citations
Ott, J., & Liu, S.-C. (2023). Biologically-Inspired Continual Learning of Human Motion Sequences. online. https://doi.org/10.1109/icassp49357.2023.10095490
