Semi-Implicit Stochastic Recurrent Neural Networks

10/28/2019
by   Ehsan Hajiramezanali, et al.
0

Stochastic recurrent neural networks with latent random variables of complex dependency structures have shown to be more successful in modeling sequential data than deterministic deep models. However, the majority of existing methods have limited expressive power due to the Gaussian assumption of latent variables. In this paper, we advocate learning implicit latent representations using semi-implicit variational inference to further increase model flexibility. Semi-implicit stochastic recurrent neural network(SIS-RNN) is developed to enrich inferred model posteriors that may have no analytic density functions, as long as independent random samples can be generated via reparameterization. Extensive experiments in different tasks on real-world datasets show that SIS-RNN outperforms the existing methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/26/2019

Variational Graph Recurrent Neural Networks

Representation learning over graph structured data has been mostly studi...
research
02/18/2019

STCN: Stochastic Temporal Convolutional Networks

Convolutional architectures have recently been shown to be competitive o...
research
11/27/2014

Learning Stochastic Recurrent Networks

Leveraging advances in variational inference, we propose to enhance recu...
research
09/15/2019

ChOracle: A Unified Statistical Framework for Churn Prediction

User churn is an important issue in online services that threatens the h...
research
09/18/2023

Latent assimilation with implicit neural representations for unknown dynamics

Data assimilation is crucial in a wide range of applications, but it oft...
research
09/01/2020

Stochastic Graph Recurrent Neural Network

Representation learning over graph structure data has been widely studie...
research
11/22/2019

Supervised and Semi-supervised Deep Learning-based Models for Indoor Location Prediction and Recognition

Predicting smartphone users location with WiFi fingerprints has been a p...

Please sign up or login with your details

Forgot password? Click here to reset