Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding
Authors: Yangxuan Zhou, Sha Zhao, Jiquan Wang, Haiteng Jiang, Shijian Li, Tao Li, Gang Pan
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Validated on three EEG datasets, SPICED show its effectiveness. More importantly, SPICED bridges biological neural mechanisms and artificial intelligence through synaptic homeostasis, providing insights into the broader applicability of bio-inspired principles. The source code is available at https://github.com/xiaobaben/SPICED. |
| Researcher Affiliation | Academia | 1State Key Laboratory of Brain-machine Intelligence, Zhejiang University 2College of Computer Science and Technology, Zhejiang University 3Department of Neurobiology, Affiliated Mental Health Center & Hangzhou Seventh People s Hospital, Zhejiang University School of Medicine 4MOE Frontier Science Center for Brain Science and Brain-machine Integration, Zhejiang University EMAIL; EMAIL; |
| Pseudocode | Yes | Algorithm 1: SPICED framework for Unsupervised Individual Continual Learning |
| Open Source Code | Yes | The source code is available at https://github.com/xiaobaben/SPICED. |
| Open Datasets | Yes | We selected three mainstream EEG-based task datasets for validation: ISRUC [56], FACED [57] and Physionet-MI [58] shown in Tab. 1. |
| Dataset Splits | Yes | Each dataset is partitioned into a pretraining set (i.e., source domain) for pre-training the source model and an incremental set (i.e., target domain) for evaluating the performance of the SPICED framework in unsupervised individual continual learning (i.e., continual EEG decoding) scenario. ... Specifically, we set varying source-target (i.e., pretrain-incremental) dataset splits (source proportions: 10%-50%) to evaluate the long-term continual EEG decoding performance of the SPICED framework under few-shot pre-training conditions. |
| Hardware Specification | Yes | And our model is trained on a single machine equipped with an Intel Core i9 10900K CPU and eight NVIDIA RTX 3080 GPUs. |
| Software Dependencies | No | The paper does not explicitly state specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions, or other libraries with their versions). |
| Experiment Setup | Yes | The detailed model architecture and pre-training process are described in the Appendix B. For each source domain individual, we initialize their synaptic nodes by storing their initial feature, labeled samples, and the pre-trained model. ... The detailed continual learning configurations and synaptic network hyper-parameters are summarized in Table 5. |