In human neuroscience, machine learning can help reveal lower-dimensional neural representations relevant to subjects' behavior. However, state-of-the-art models typically require large datasets to train, so are prone to overfitting on human neuroimaging data that often possess few samples but many input dimensions. Here, we capitalized on the fact that the features we seek in human neuroscience are precisely those relevant to subjects' behavior. We thus developed a Task-Relevant Autoencoder via Classifier Enhancement (TRACE), and tested its ability to extract behaviorally-relevant, separable representations compared to a standard autoencoder, a variational autoencoder, and principal component analysis for two severely truncated machine learning datasets. We then evaluated all models on fMRI data from 59 subjects who observed animals and objects. TRACE outperformed all models nearly unilaterally, showing up to 12% increased classification accuracy and up to 56% improvement in discovering "cleaner", task-relevant representations. These results showcase TRACE's potential for a wide variety of data related to human behavior.

翻译：在人类神经科学中，机器学习有助于揭示与受试者行为相关的低维神经表征。然而，当前最先进的模型通常需要大规模数据集进行训练，因此在面对样本数量少但输入维度高的人类神经影像数据时容易过拟合。在此，我们利用了人类神经科学中寻求的特征恰好与受试者行为相关这一事实，进而开发了一种通过分类器增强的任务相关自编码器（TRACE），并与标准自编码器、变分自编码器及主成分分析进行对比，测试其在两个严重截断的机器学习数据集上提取行为相关、可分表征的能力。随后，我们使用59名观察动物和物件的受试者的功能磁共振成像数据对所有模型进行了评估。TRACE几乎在所有方面均优于其他模型，分类准确率提升高达12%，在发现"更清晰"的任务相关表征方面改进幅度达56%。这些结果展示了TRACE在涉及人类行为的各类数据中的巨大潜力。