Variational Recurrent Auto-Encoders

2014/12/20 by Otto Fabius, Fabius, Otto, Joost R. van Amersfoort +1 · 6 citations
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE) #cs.LG #cs.NE #stat.ML

paper · pdf · doi:10.48550/arxiv.1412.6581

Accepted at ICLR workshop track

arxiv created 2015/06/15 · arxiv updated 2015/06/16

Abstract

In this paper we propose a model that combines the strengths of RNNs and SGVB: the Variational Recurrent Auto-Encoder (VRAE). Such a model can be used for efficient, large scale unsupervised learning on time series data, mapping the time series data to a latent vector representation. The model is generative, such that data can be generated from samples of the latent space. An important contribution of this work is that the model can make use of unlabeled data in order to facilitate supervised training of RNNs by initialising the weights and network state.

Cited by

• Towards Comprehensive Information-theoretic Multi-view Learning
• FairDRL-ST: Disentangled Representation Learning for Fair Spatio-Temporal Mobility Prediction
• Ground Reaction Force Estimation via Time-aware Knowledge Distillation
• Alternators With Noise Models
• 4TaStiC: Time and trend traveling time series clustering for classifying long-term type 2 diabetes patients
• Generative Models for Long Time Series: Approximately Equivariant Recurrent Network Structures for an Adjusted Training Scheme

Related

• Generative Models for Long Time Series: Approximately Equivariant Recurrent Network Structures for an Adjusted Training Scheme
• Multi-Decoder RNN Autoencoder Based on Variational Bayes Method
• TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation
• A Recurrent Latent Variable Model for Sequential Data
• Variational Hyper RNN for Sequence Modeling