We propose a model for hierarchical structured data as an extension to the stochastic temporal convolutional network. The proposed combines autoregressive with variational autoencoder and downsampling achieve superior computational complexity. evaluate on two different types of sequential data: speech handwritten text. results are promising achieving state-of-the-art performance.

Those of us who study human cognition have no easy task. We try to understand how people functionally represent and processes information in performing cognitive activities such as vision, perception, memory, language, and decision making. Fortunately, experimental psychology has a rich theoretical tradition, and there is no shortage of insightful theoretical proposals. Also, it has a rich expe...

Methods for spatial and spatio-temporal modeling are becoming increasingly important in environmental sciences and other sciences where data arise from a process in an inherent spatial setting. Technological advances in remote sensing, monitoring networks, and other methods of collecting spatial data in recent decades have revolutionized scientific endeavor in fields such as agriculture, climat...

Black box variational inference allows researchers to easily prototype and evaluate an array of models. Recent advances allow such algorithms to scale to high dimensions. However, a central question remains: How to specify an expressive variational distribution that maintains efficient computation? To address this, we develop hierarchical variational models (HVMs). HVMs augment a variational ap...

This paper presents an approach to dynamic factor modeling in which variations can be idiosyncratic, block-specific, or common across blocks and units. Existing two level factor models do not usually account for variations at the block level which implies that these can be confounded with genuine common co-movements in the data. Specifying the block structure also facilitates interpretation of ...