Sorry, you need to enable JavaScript to visit this website.

Biologically-Inspired Continual Learning of Human Motion Sequences

Citation Author(s):
Joachim Ott, Shih-Chii Liu
Submitted by:
Joachim Ott
Last updated:
17 November 2023 - 12:07pm
Document Type:
Document Year:
Joachim Ott

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 over a set of tasks. The final classification accuracy of BI-CTVAE on a human motion dataset after sequentially learning all action classes is 78%, which is 63% higher than using no-replay, and only 5.4% lower than a state-of-the-art offline trained GRU model.

0 users have voted: