Paired Trial Classification: A Novel Deep Learning Technique for MVPA
Paired Trial Classification: A Novel Deep Learning Technique for MVPA
复制标题
DOI：
10.3389/fnins.2020.00417
复制
发表时间：
2020-04
影响因子：
4.3
通讯作者：
Jacob M. Williams;A. Samal;Prahalada K. Rao;Matthew R. Johnson
中科院分区：
文献类型：
--
作者：
Jacob M. Williams;A. Samal;Prahalada K. Rao;Matthew R. Johnson
机器学习的许多最新发展都来自“深度学习”领域，或使用先进的神经网络架构和技术。虽然这些方法已经产生了最先进的结果，并主导了许多领域的研究重点，如图像分类和自然语言处理，但在脑电图（EEG）或其他人类神经科学数据集的分类中，它们并没有获得与标准多变量模式分析（MVPA）技术一样多的基础。EEG数据中存在的高维度和大量噪声，加上可以从人类受试者样本中合理获得的相对较少的示例（试验），导致难以训练深度学习模型。即使模型在训练中成功收敛，尽管存在正则化技术，也可能发生显著的过拟合。为了帮助缓解这些问题，我们提出了一种新的方法“配对试验分类”，涉及分类对EEG记录来自同一类或不同的类。这使我们能够通过配对试验的组合学，以类似于但不同于传统数据增强方法的方式大幅增加训练示例的数量。此外，配对试验分类仍然允许我们通过“字典”方法确定新示例（试验）的真实类别：将新示例与每个类别的一组已知示例进行比较，并通过对每个类别内相同/不同的决策值进行求和来确定最终类别。由于个别试验是嘈杂的，这种方法可以通过比较一个新的个别例子与“字典”，其中每个条目是几个例子（试验）的平均值，进一步改进。在可以对来自单个未知类的多个样本进行平均的情况下，甚至可以实现进一步的改进，从而允许将平均信号与平均信号进行比较。
Many recent developments in machine learning have come from the field of “deep learning,” or the use of advanced neural network architectures and techniques. While these methods have produced state-of-the-art results and dominated research focus in many fields, such as image classification and natural language processing, they have not gained as much ground over standard multivariate pattern analysis (MVPA) techniques in the classification of electroencephalography (EEG) or other human neuroscience datasets. The high dimensionality and large amounts of noise present in EEG data, coupled with the relatively low number of examples (trials) that can be reasonably obtained from a sample of human subjects, lead to difficulty training deep learning models. Even when a model successfully converges in training, significant overfitting can occur despite the presence of regularization techniques. To help alleviate these problems, we present a new method of “paired trial classification” that involves classifying pairs of EEG recordings as coming from the same class or different classes. This allows us to drastically increase the number of training examples, in a manner akin to but distinct from traditional data augmentation approaches, through the combinatorics of pairing trials. Moreover, paired trial classification still allows us to determine the true class of a novel example (trial) via a “dictionary” approach: compare the novel example to a group of known examples from each class, and determine the final class via summing the same/different decision values within each class. Since individual trials are noisy, this approach can be further improved by comparing a novel individual example with a “dictionary” in which each entry is an average of several examples (trials). Even further improvements can be realized in situations where multiple samples from a single unknown class can be averaged, thus permitting averaged signals to be compared with averaged signals.