Scheduled Knowledge Acquisition on Lightweight Vector Symbolic Architectures for Brain-Computer Interfaces

arXiv:2403.13844v1 Announce Type: new
Abstract: Brain-Computer interfaces (BCIs) are typically designed to be lightweight and responsive in real-time to provide users timely feedback. Classical feature engineering is computationally efficient but has low accuracy, whereas the recent neural networks (DNNs) improve accuracy but are computationally expensive and incur high latency. As a promising alternative, the low-dimensional computing (LDC) classifier based on vector symbolic architecture (VSA), achieves small model size yet higher accuracy than classical feature engineering methods. However, its accuracy still …

abstract accuracy acquisition architectures arxiv brain computer cs.ai cs.lg engineering feature feature engineering feedback interfaces knowledge knowledge acquisition latency low networks neural networks real-time responsive type vector