Biologically-Inspired Continual Learning of Human Motion Sequences
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningTemporal SequencesMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning
Humans excel at continually acquiring, consolidating, and retaining information from an ever-changing environment, whereas artificial neural networks (ANNs) exhibit catastrophic forgetting. There are considerable differe…
Continual LearningMI-DETR: A Strong Baseline for Moving Infrared Small Target Detection with Bio-Inspired Motion Integration
Infrared small target detection (ISTD) is challenging because tiny, low-contrast targets are easily obscured by complex and dynamic backgrounds. Conventional multi-frame approaches typically learn motion implicitly throu…
CLASSP: a Biologically-Inspired Approach to Continual Learning through Adjustment Suppression and Sparsity Promotion
This paper introduces a new biologically-inspired training method named Continual Learning through Adjustment Suppression and Sparsity Promotion (CLASSP). CLASSP is based on two main principles observed in neuroscience, …
Continual LearningSentiment AnalysisSparse LearningCL-BioGAN: Biologically-Inspired Cross-Domain Continual Learning for Hyperspectral Anomaly Detection
Memory stability and learning flexibility in continual learning (CL) is a core challenge for cross-scene Hyperspectral Anomaly Detection (HAD) task. Biological neural networks can actively forget history knowledge that c…
Anomaly DetectionContinual LearningGenerative Adversarial NetworkLearning to Learn with Feedback and Local Plasticity
Interest in biologically inspired alternatives to backpropagation is driven by the desire to both advance connections between deep learning and neuroscience and address backpropagation's shortcomings on tasks such as onl…
Continual LearningMeta-Learning