研究人员开发了GRAFT，一个基于Transformer的模型，用于神经种群活动建模。该新模型将可重用的时间动态与可重新校准的神经元接口分开，从而在神经元身份和统计数据可能发生变化的脑机接口中实现更好的适应性。GRAFT在NLB'21协议上取得了新的最先进性能，达到了0.3866 co-bps。此外，它通过仅更新一小部分参数，展示了高效的跨日重新校准能力。 AI
影响 在神经种群活动建模方面创下新的SOTA，可能改进脑机接口。
排序理由 该集群包含一篇详细介绍新模型及其在基准测试中性能的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.11066v1 Announce Type: new Abstract: Neural population activity models can recover rich temporal structure from binned spikes, but their read-in and readout layers often remain tied to a fixed set of recorded neurons. This coupling limits reuse in long-term brain-compu…
Neural population activity models can recover rich temporal structure from binned spikes, but their read-in and readout layers often remain tied to a fixed set of recorded neurons. This coupling limits reuse in long-term brain-computer interfaces, where recorded neuron identities…