Date of Original Version



Technical Report

Rights Management

All Rights Reserved

Abstract or Description

Abstract: "We introduce the Hidden Process Model (HPM), a probabilistic model for multivariate time series data intended to model complex, poorly understood, overlapping and linearly additive processes. HPMs are motivated by our interest in modeling cognitive processes given brain image data. We define HPMs, present inference and learning algorithms, study their characteristics using synthetic data, and demonstrate their use for tracking human cognitive processes using fMRI data."