Department of Computational Brain Imaging, Advanced Telecommunication Research Institute International, Kyoto, Japan.
Department of Computational Brain Imaging, Advanced Telecommunication Research Institute International, Kyoto, Japan; Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan.
Neural Netw. 2023 Jun;163:327-340. doi: 10.1016/j.neunet.2023.03.038. Epub 2023 Apr 17.
The recent success of sequential learning models, such as deep recurrent neural networks, is largely due to their superior representation-learning capability for learning the informative representation of a targeted time series. The learning of these representations is generally goal-directed, resulting in their task-specific nature, giving rise to excellent performance in completing a single downstream task but hindering between-task generalisation. Meanwhile, with increasingly intricate sequential learning models, learned representation becomes abstract to human knowledge and comprehension. Hence, we propose a unified local predictive model based on the multi-task learning paradigm to learn the task-agnostic and interpretable subsequence-based time series representation, allowing versatile use of learned representations in temporal prediction, smoothing, and classification tasks. The targeted interpretable representation could convey the spectral information of the modelled time series to the level of human comprehension. Through a proof-of-concept evaluation study, we demonstrate the empirical superiority of learned task-agnostic and interpretable representation over task-specific and conventional subsequence-based representation, such as symbolic and recurrent learning-based representation, in solving temporal prediction, smoothing, and classification tasks. These learned task-agnostic representations can also reveal the ground-truth periodicity of the modelled time series. We further propose two applications of our unified local predictive model in functional magnetic resonance imaging (fMRI) analysis to reveal the spectral characterisation of cortical areas at rest and reconstruct more smoothed temporal dynamics of cortical activations in both resting-state and task-evoked fMRI data, giving rise to robust decoding.
近年来，顺序学习模型（如深度递归神经网络）取得了巨大成功，这主要归功于它们在学习目标时间序列信息表示方面的卓越表示学习能力。这些表示的学习通常是有目的的，导致它们具有任务特定的性质，在完成单个下游任务方面表现出色，但阻碍了任务间的泛化。同时，随着顺序学习模型变得越来越复杂，所学到的表示对于人类的知识和理解变得抽象。因此，我们提出了一种基于多任务学习范例的统一局部预测模型，以学习与任务无关且可解释的基于子序列的时间序列表示，允许在时间预测、平滑和分类任务中灵活使用学习到的表示。目标可解释表示可以将建模时间序列的谱信息传达给人类理解的水平。通过概念验证评估研究，我们证明了学习到的与任务无关且可解释的表示在解决时间预测、平滑和分类任务方面优于特定任务和传统基于子序列的表示，例如符号和基于递归的表示。这些学习到的与任务无关的表示还可以揭示建模时间序列的真实周期性。我们进一步提出了我们的统一局部预测模型在功能磁共振成像（fMRI）分析中的两个应用，以揭示静息状态下皮质区域的频谱特征，并重建静息态和任务诱发 fMRI 数据中皮质激活的更平滑时间动态，从而实现稳健解码。
