Toward Lightweight and Fast Inference Neural Decoder Design using Quantization-Aware Training: A Simulation Study
Developing lightweight neural decoders with fast inference speed will advance brain-computer interfaces (BCIs) for real-time applications. However, current neural decoder designs are mainly based on deep neural networks with high floating precision, l
Authors
- Bo-Cheng Charles Lai (ORCID: https://orcid.org/0000-0002-9729-5196)
- Amy L. Orsborn (ORCID: https://orcid.org/0000-0003-4131-5781)
- Eli Shlizerman (ORCID: https://orcid.org/0000-0002-3136-4531)
- Trung Le (ORCID: https://orcid.org/0000-0002-7047-8451)
- Hao Fang (ORCID: https://orcid.org/0000-0003-3800-4800)
- Jing Li (ORCID: https://orcid.org/0000-0002-2256-9818)
- C. H. Chen
Institutions
- National Yang Ming Chiao Tung University (TW)
- University of Washington (US)
Publication Details
- Published
- 2025-08-26
- DOI
- https://doi.org/10.36227/techrxiv.175624503.30111847/v1
- Primary Topic
- Neural Networks and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Science Foundation
- University of Washington