在LFADS模型中提高可解释性,使用学习的,上下文依赖的每试验偏差
Nishal P Shah1, Benyamin Abramovich Krasa2, Erin Kunz2
1Rice University.
bioRxiv : the preprint server for biology
|November 19, 2025
概括
我们介绍了上下文LFADS,一种使用动态系统 (LFADS) 模型的修改后隐性因子分析. 这提高了神经动态的可解释性,使其能够适应特定的上下文,改善了脑计算机接口 (BCI) 应用程序.
科学领域:
- 计算神经科学是一种计算神经科学.
- 动态系统理论 动态系统理论
- 机器学习用于神经科学
背景情况:
- 生物神经回路通过不断演变的内部状态来处理信息.
- 使用动态系统 (LFADS) 进行潜伏因子分析,用RNNs模拟神经活动,但由于复杂的动态,其解释性不佳.
研究的目的:
- 为了提高神经动力学LFADS模型的解释性.
- 开发一个修改后的LFADS模型,以捕获试验特定的上下文信息.
- 为了应对脑电脑界面 (BCI) 数据分析方面的挑战.
主要方法:
- 在LFADS循环神经网络 (RNN) 生成器中引入了每试验偏差.
- 模拟每次试验偏差作为一个不断输入的上下文适应.
- 在模拟和真实神经记录上测试了修改后的模型 (上下文LFADS).
主要成果:
- 标准的LFADS表现出复杂的,多稳定的动态;上下文的LFADS学习了更简单的,可解释的动态.
- 语境LFADS能够进行单一试验分析,重现试验平均结果.
- 修改后的模型解决了BCI记录中的非静止性和行为变化.
结论:
- 语境LFADS提供了一个更易于解释的神经动态模型.
- 每次试验偏差修改增强了LFADS用于分析神经数据和BCI的实用性.
- 这种方法为理解和利用神经信号提供了一个有前途的方法.
更多相关视频
09:27Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
Published on: October 13, 2018
10.6K
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
8.0K
相关概念视频
01:12Hindsight Biases
4.2K
Hindsight bias leads you to believe that the event you just experienced was predictable, even though it really wasn’t. In other words, you knew all along that things would turn out the way they did. Can you relate this to the phrase "Hindsight is 20/20" now?
4.2K
01:22Biasing of FET
659
Biasing a Junction Field Effect Transistor (JFET) is crucial for setting operational parameters and ensuring efficient functioning in electronic circuits. JFETs are characterized by using a single carrier type in N-channel or P-channel configurations, where the channel is surrounded by PN junctions. These junctions are central to the device's ability to control current flow.
In an N-channel JFET, the structure consists of N-type material forming the channel on a P-type substrate, with the...
In an N-channel JFET, the structure consists of N-type material forming the channel on a P-type substrate, with the...
659