为了实现单细胞,单尖分辨率的神经动态的"通用翻译器"
Yizi Zhang1, Yanchen Wang1, Donato M Jiménez-Benetó2
1Columbia University.
Advances in neural information processing systems
|July 7, 2025
概括
研究人员开发了一种用于神经增强数据的新型基础模型. 这种多任务掩盖 (MtM) 方法改善了大脑活动的预测,并使多个动物能够进行多任务学习.
科学领域:
- 神经科学是一个神经科学.
- 计算神经科学是一种神经科学.
- 机器学习 机器学习
背景情况:
- 目前神经科学对大脑的理解是分散的.
- 从任意大脑区域读取神经活动仍然是一个挑战.
研究的目的:
- 为神经增数据开发一个基础模型.
- 为了实现神经活动中编码信息的自动读取.
主要方法:
- 引入了一种新的自我监督建模方法:多任务掩盖 (MtM).
- MtM模型在掩盖和重建神经活动之间交替,跨时间,神经元和大脑区域.
- 使用国际大脑实验室数据集与48只动物的Neuropixels记录进行评估.
主要成果:
- MtM显著改善了与最先进的人口模型相比的性能.
- 启用有效的多任务学习,用于各种预测任务 (单个神经元,区域级,前预测,行为解码).
- 在多个动物上进行训练,增强了对未见对象的模型概括性.
结论:
- MtM方法为全面的大脑模型提供了基础.
- 这项工作推进了理解单细胞,单分辨率的大脑功能的目标.
- 开发的模型为大脑的通用基础模型铺平了道路.
相关概念视频
02:07Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
02:07Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...