Variational Hyper RNN for Sequence Modeling

Abstract

In this work, we propose a novel probabilistic sequence model that excels at capturing high variability in time series data, both across sequences and within an individual sequence. Our method uses temporal latent variables to capture information about the underlying data pattern and dynamically decodes the latent information into modifications of weights of the base decoder and recurrent model. The efficacy of the proposed method is demonstrated on a range of synthetic and real-world sequential data that exhibit large scale variations, regime shifts, and complex dynamics.

References in corpus (3)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
• Online Decorrelation of Humidity and Temperature in Chemical Sensors for Continuous Monitoring