Date of this Version
Williams JM, Samal A, Rao PK and Johnson MR (2020) Paired Trial Classiﬁcation: A Novel Deep Learning Technique for MVPA. Front. Neurosci. 14:417. doi: 10.3389/fnins.2020.00417
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.