Autoencoder Based Residual Deep Networks for Robust Regression Prediction and Spatiotemporal Estimation

12/29/2018
by   Lianfa Li, et al.
14

To have a superior generalization, a deep learning neural network often involves a large size of training sample. With increase of hidden layers in order to increase learning ability, neural network has potential degradation in accuracy. Both could seriously limit applicability of deep learning in some domains particularly involving predictions of continuous variables with a small size of samples. Inspired by residual convolutional neural network in computer vision and recent findings of crucial shortcuts in the brains in neuroscience, we propose an autoencoder-based residual deep network for robust prediction. In a nested way, we leverage shortcut connections to implement residual mapping with a balanced structure for efficient propagation of error signals. The novel method is demonstrated by multiple datasets, imputation of high spatiotemporal resolution non-randomness missing values of aerosol optical depth, and spatiotemporal estimation of fine particulate matter <2.5 μ m, achieving the cutting edge of accuracy and efficiency. Our approach is also a general-purpose regression learner to be applicable in diverse domains.

READ FULL TEXT

page 5

page 7

page 8

research
05/05/2017

Residual Squeeze VGG16

Deep learning has given way to a new era of machine learning, apart from...
research
06/15/2017

The Compressed Model of Residual CNDS

Convolutional neural networks have achieved a great success in the recen...
research
05/09/2022

Predicting parametric spatiotemporal dynamics by multi-resolution PDE structure-preserved deep learning

Although recent advances in deep learning (DL) have shown a great promis...
research
05/28/2016

Weighted Residuals for Very Deep Networks

Deep residual networks have recently shown appealing performance on many...
research
05/13/2022

Convergence Analysis of Deep Residual Networks

Various powerful deep neural network architectures have made great contr...
research
05/03/2021

Representation Learning using Graph Autoencoders with Residual Connections

Graph autoencoders are very efficient at embedding graph-based complex d...
research
01/15/2021

A Novel Prediction Approach for Exploring PM2.5 Spatiotemporal Propagation Based on Convolutional Recursive Neural Networks

The spread of PM2.5 pollutants that endanger health is difficult to pred...

Please sign up or login with your details

Forgot password? Click here to reset