Modern Machine Learning as a Benchmark for Fitting Neural Responses.

Modern Machine Learning as a Benchmark for Fitting Neural Responses.
复制标题

DOI:
10.3389/fncom.2018.00056
复制
发表时间:
2018
影响因子:
3.2
通讯作者:
Kording KP
Kording KP
中科院分区:
医学4区
文献类型:
--
作者:
Benjamin AS;Fernandes HL;Tomlinson T;Ramkumar P;VerSteeg C;Chowdhury RH;Miller LE;Kording KP

文献摘要

参考文献

被引文献

相似文献

长期以来,神经科学一直专注于寻找编码模型,这些模型可以有效地询问“是什么预测了神经尖峰?”广义线性模型(GLMS)是一种典型的方法。在对模型进行拟合时,人们通常不知道有多少可解释的神经活动被捕捉到或错过了。在这里,我们将简单模型的预测性能与三种主要的机器学习方法进行了比较:前馈神经网络、梯度增强树(使用XGBoost)和组合了几种方法预测的堆叠集成。我们从到达运动学的标准表示中预测了猕猴运动(M1)和躯体感觉(S1)皮质中的尖峰计数,并从开阔的位置和方向预测了大鼠海马细胞中的尖峰计数。在这些方法中,XGBoost和集成始终产生更准确的尖峰率预测,并且对特征的预处理不那么敏感。因此,可以快速应用这些方法来检测特征集是否与神经活动相关,这种方式不是更简单的方法所能捕捉到的。使用机器学习方法构建的编码模型可以准确预测峰值速率,并可以为更简单的模型提供有意义的基准。
Neuroscience has long focused on finding encoding models that effectively ask “what predicts neural spiking?” and generalized linear models (GLMs) are a typical approach. It is often unknown how much of explainable neural activity is captured, or missed, when fitting a model. Here we compared the predictive performance of simple models to three leading machine learning methods: feedforward neural networks, gradient boosted trees (using XGBoost), and stacked ensembles that combine the predictions of several methods. We predicted spike counts in macaque motor (M1) and somatosensory (S1) cortices from standard representations of reaching kinematics, and in rat hippocampal cells from open field location and orientation. Of these methods, XGBoost and the ensemble consistently produced more accurate spike rate predictions and were less sensitive to the preprocessing of features. These methods can thus be applied quickly to detect if feature sets relate to neural activity in a manner not captured by simpler methods. Encoding models built with a machine learning approach accurately predict spike rates and can offer meaningful benchmarks for simpler models.
DOI: 10.3389/fncom.2010.00012
发表时间: 2010
影响因子: 3.2
作者:
Gerwinn S;Macke JH;Bethge M
通讯作者: Bethge M
DOI: 10.1162/089976600300015015
发表时间: 2000-10-01
期刊: NEURAL COMPUTATION
影响因子: 2.9
作者:
Gers, FA;Schmidhuber, J;Cummins, F
通讯作者: Cummins, F
DOI: 10.1016/j.neuron.2016.05.039
发表时间: 2016-07-20
期刊: Neuron
影响因子: 16.2
作者:
Aljadeff J;Lansdell BJ;Fairhall AL;Kleinfeld D
通讯作者: Kleinfeld D
DOI: 10.1109/34.709601
发表时间: 1998-08-01
影响因子: 23.6
作者:
Ho, TK
通讯作者: Ho, TK
DOI: 10.1214/aos/1013203451
发表时间: 2001-10-01
影响因子: 4.5
作者:
Friedman, JH
通讯作者: Friedman, JH