Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference

01/17/2019
by   Xinyu Hu, et al.
0

A regression-based BNN model is proposed to predict spatiotemporal quantities like hourly rider demand with calibrated uncertainties. The main contributions of this paper are (i) A feed-forward deterministic neural network (DetNN) architecture that predicts cyclical time series data with sensitivity to anomalous forecasting events; (ii) A Bayesian framework applying SVGD to train large neural networks for such tasks, capable of producing time series predictions as well as measures of uncertainty surrounding the predictions. Experiments show that the proposed BNN reduces average estimation error by 10 across 8 U.S. cities compared to a fine-tuned multilayer perceptron (MLP), and 4

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/07/2014

Time series forecasting using neural networks

Recent studies have shown the classification and prediction power of the...
research
05/12/2016

Direct Method for Training Feed-forward Neural Networks using Batch Extended Kalman Filter for Multi-Step-Ahead Predictions

This paper is dedicated to the long-term, or multi-step-ahead, time seri...
research
11/11/2022

Comparison of Uncertainty Quantification with Deep Learning in Time Series Regression

Increasingly high-stakes decisions are made using neural networks in ord...
research
09/06/2017

Deep and Confident Prediction for Time Series at Uber

Reliable uncertainty estimation for time series prediction is critical i...
research
02/11/2020

ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series Forecasting

Recurrent and convolutional neural networks are the most common architec...
research
02/08/2022

KENN: Enhancing Deep Neural Networks by Leveraging Knowledge for Time Series Forecasting

End-to-end data-driven machine learning methods often have exuberant req...
research
01/20/2019

Explainable Failure Predictions with RNN Classifiers based on Time Series Data

Given key performance indicators collected with fine granularity as time...

Please sign up or login with your details

Forgot password? Click here to reset