Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Altered Lighting Conditions Elicit Sex-Specific Circadian Behaviors in Diurnal Grass Rats.

bioRxiv : the preprint server for biology·2026
Same author

SpikeCleaner: An Algorithm to Label Unit Quality After Automated Spike Sorting.

bioRxiv : the preprint server for biology·2026
Same authorSame journal

Long-term Intracortical Neural activity and Kinematics (LINK): An intracortical neural dataset for chronic brain-machine interfaces, neuroscience, and machine learning.

Advances in neural information processing systems·2026
Same author

Use of RPNIs and Implanted Electrodes for Prosthetic Wrist and Multi-Grip Hand Control during Functional Tasks: A Case Study.

IEEE transactions on bio-medical engineering·2026
Same author

Exploring Synergies in Brain-Machine Interfaces: Compression vs. Performance.

Restorative neurology and neuroscience·2026
Same author

A Roadmap to Navigate the Future of Neural Engineering.

Journal of neural engineering·2026
Same journal

QuanDA: Quantile-Based Discriminant Analysis for High-Dimensional Imbalanced Classification.

Advances in neural information processing systems·2026
Same journal

Analysis of Variance of Multiple Causal Networks.

Advances in neural information processing systems·2026
Same journal

Distributionally Robust Feature Selection.

Advances in neural information processing systems·2026
Same journal

On the Identifiability of Hybrid Deep Generative Models: Meta-Learning as a Solution.

Advances in neural information processing systems·2026
Same journal

Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time.

Advances in neural information processing systems·2026
查看所有相关文章

相关实验视频

Updated: May 13, 2025

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

13.6K

探索深度学习和可解释的大脑机器接口模型之间的权衡.

Luis H Cubillos1, Guy Revach2, Matthew J Mender1

  • 1Departments of Electrical & Computer Engineering, Biomedical Engineering, Robotics, Computational Medicine & Bioinformatics, and Neurosurgery, University of Michigan, USA.

Advances in neural information processing systems
|April 15, 2025
PubMed
概括
此摘要是机器生成的。

这项研究介绍了KalmanNet,一种新的脑机界面 (BMI) 解码器,该解码器将Kalman波器 (KF) 的可解释性与患者的深度学习性能相结合. KalmanNet在预测运动方面实现了高精度,为当前的深度学习模型提供了更安全,更易于解释的替代方案.

更多相关视频

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring
06:32

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Published on: July 14, 2023

1.1K
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

8.8K

相关实验视频

Last Updated: May 13, 2025

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces
10:51

An Experimental Platform to Study the Closed-loop Performance of Brain-machine Interfaces

Published on: March 10, 2011

13.6K
Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring
06:32

Author Spotlight: Automated Deep Brain Stimulation for Parkinson's Disease - Exploring the Possibilities and Challenges of Home Monitoring

Published on: July 14, 2023

1.1K
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

8.8K

科学领域:

  • 神经科学是一个神经科学.
  • 生物医学工程 生物医学工程
  • 机器学习 机器学习

背景情况:

  • 大脑机器接口 (BMI) 通过将大脑活动解码为运动命令,为患者提供了一个潜在的解决方案.
  • 深度学习解码器在BMI中实现了高性能,但由于其"黑子"性质,引发了安全问题.
  • 尽管性能较低,可解释解码器如卡尔曼波器 (KF) 经常被使用.

研究的目的:

  • 开发和评估KalmanNet,这是一种新的BMI解码器,它将KF可解释性与反复的神经网络集成在一起.
  • 将KalmanNet的性能与传统的KF和深度学习模型 (tcFNN,LSTM) 进行比较,以预测手指运动.
  • 评估BMI解码器中的性能,可解释性和概括性之间的权衡.

主要方法:

  • 开发了KalmanNet,这是KF的扩展,使用循环神经网络计算Kalman增益,允许输入和动态之间的动态信任转移.
  • 使用Kalman.Net.使用子大脑活动预测手指运动.
  • 与KF,tcFNN和LSTM相比,比较了KalmanNet的线下和在线性能.
  • 验证了机制与一个异种KF.

主要成果:

  • 在线和离线环境中,KalmanNet实现了与深度学习模型相比或优于深度学习模型的性能.
  • 卡尔曼网展示了灵活依赖动态模型的动作启动和停止的神经输入.
  • 使用相同策略的异种KF也接近了最先进的性能,同时保持了可解释性.
  • KalmanNet在概括和性能方面表现出局限性,与其他深度学习解码器相似的未见噪声分布.

结论:

  • KalmanNet成功地将传统和深度学习方法集成到高性能,可解释的BMI解码器中.
  • 该研究强调了混合模型在提高BMI安全性和可靠性方面的潜力.
  • 需要进一步的研究来解决更广泛的临床应用的泛化局限性.