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.

翻译：本文提出了一种用于连续学习时间序列任务（特别是人类运动）的模型。该模型基于近期提出的脑启发式回放模型（BI-R）进行改进，通过构建一个受生物学启发的条件时序变分自编码器（BI-CTVAE），实例化了用于类别表示的潜变量高斯混合分布。我们研究了一种新颖的连续学习生成（CL2Gen）场景，其中模型生成不同类别的运动序列。通过一系列任务测试了模型的生成准确率。在依次学习所有动作类别后，BI-CTVAE在人类运动数据集上的最终分类准确率达到78%，比不使用回放的方法高出63%，仅比最先进的离线训练GRU模型低5.4%。