Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Learning temporal evolution of probability distribution with Recurrent Neural Network
Kyongmin Yeo, Igor Melnyk, Nam Nguyen, Eun Kyung Lee
Feb 15, 2018 (modified: Feb 15, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:We propose to tackle a time series regression problem by computing temporal evolution of a probability density function to provide a probabilistic forecast. A Recurrent Neural Network (RNN) based model is employed to learn a nonlinear operator for temporal evolution of a probability density function. We use a softmax layer for a numerical discretization of a smooth probability density functions, which transforms a function approximation problem to a classification task. Explicit and implicit regularization strategies are introduced to impose a smoothness condition on the estimated probability distribution. A Monte Carlo procedure to compute the temporal evolution of the distribution for a multiple-step forecast is presented. The evaluation of the proposed algorithm on three synthetic and two real data sets shows advantage over the compared baselines.
TL;DR:Proposed RNN-based algorithm to estimate predictive distribution in one- and multi-step forecasts in time series prediction problems
Keywords:predictive distribution estimation, probabilistic RNN, uncertainty in time series prediction
Enter your feedback below and we'll get back to you as soon as possible.