可解释的深度学习用于神经信号的解密分析
Bahareh Tolooshams1, Sara Matias2, Hao Wu2
1Center for Brain Science, Harvard University, Cambridge, MA 02138, USA; John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA; Computing + mathematical sciences, California Institute of Technology, Pasadena, CA 91125, USA.
Neuron
|March 13, 2025
概括
我们介绍了解构无卷神经学习 (DUNL),一种可解释的深度学习方法. DUNL将神经活动与网络参数连接起来,揭示大脑信号和神经反应特征.
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
- 神经科学是一个神经科学.
背景情况:
- 深度学习模拟神经活动,但往往充当"黑子".
- 缺乏可解释性阻碍了理解神经活动与网络参数之间的联系.
研究的目的:
- 开发一种可解释的深度学习方法来分析神经活动.
- 使用生成模型建立与神经活动相关的网络权重的直接解释.
主要方法:
- 算法展开设计稀疏的解卷神经网络.
- 介绍解卷式未卷式神经学习 (DUNL).
- 应用DUNL来解脑区域和记录方式的单试本地信号.
主要成果:
- 在多巴胺神经元中发现了多重突出和奖励预测错误信号.
- 在体感性丘脑中进行了同时事件检测和表征.
- 在自然主义实验中,在piriform皮质和条纹体中表现出异质的神经反应.
结论:
- DUNL提供了对神经活动的机制性理解.
- 可解释深度学习的进步为大脑功能提供了新的见解.
- 在不同的大脑区域和记录类型中,DUNL表现出了多功能性.
相关概念视频
01:20Deconvolution
127
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...
127
01:24Convolution: Math, Graphics, and Discrete Signals
219
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...
219