可解释的深度学习用于神经信号的解密分析
Bahareh Tolooshams1,2,3, Sara Matias1,4, Hao Wu1,4
1Center for Brain Science, Harvard University, Cambridge MA, 02138.
bioRxiv : the preprint server for biology
|January 23, 2024
概括
我们介绍了Deconvolutional Unrolled Neural Learning (DUNL),一种可解释的深度学习方法. DUNL将神经活动与网络参数联系起来,使神经动态的机制理解成为可能.
科学领域:
- 计算神经科学是一种神经科学.
- 机器学习 机器学习
- 系统神经科学 系统神经科学
背景情况:
- 神经动态的深度学习模型往往缺乏可解释性.
- 了解神经活动与网络参数之间的联系至关重要.
研究的目的:
- 开发一种可解释的深度学习方法来分析神经群体动态.
- 使用生成模型,建立神经活动和网络参数之间的直接联系.
主要方法:
- 运用于设计稀疏解卷神经网络的算法解卷.
- 开发了Deconvolutional Unrolled神经学习 (DUNL) 框架. 开发了Deconvolutional无名神经学习 (DUNL) 框架.
- 在多个大脑区域和记录方式中应用到单次试验的局部信号.
主要成果:
- DUNL提供与刺激驱动活动相关的可解释的网络权重.
- 在不同大脑区域 (中脑,体感性丘脑,皮质皮质,状体) 成功解构单个试验信号.
- 在多巴胺神经元中发现了多重突出和奖励预测错误信号.
- 执行了同时发生事件的检测和描述.
- 在自然主义实验中表现出异质的神经反应.
结论:
- 通过可解释的深度学习,DUNL提供了对神经活动的机制性理解.
- 该方法对于分析多样化的神经记录具有多样性.
- 为神经科学研究推进可解释的人工智能.
相关概念视频
01:20Deconvolution
160
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
160
01:24Convolution: Math, Graphics, and Discrete Signals
261
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
261