Autoencoder based Randomized Learning of Feedforward Neural Networks for Regression

by   Grzegorz Dudek, et al.

Feedforward neural networks are widely used as universal predictive models to fit data distribution. Common gradient-based learning, however, suffers from many drawbacks making the training process ineffective and time-consuming. Alternative randomized learning does not use gradients but selects hidden node parameters randomly. This makes the training process extremely fast. However, the problem in randomized learning is how to determine the random parameters. A recently proposed method uses autoencoders for unsupervised parameter learning. This method showed superior performance on classification tasks. In this work, we apply this method to regression problems, and, finding that it has some drawbacks, we show how to improve it. We propose a learning method of autoencoders that controls the produced random weights. We also propose how to determine the biases of hidden nodes. We empirically compare autoencoder based learning with other randomized learning methods proposed recently for regression and find that despite the proposed improvement of the autoencoder based learning, it does not outperform its competitors in fitting accuracy. Moreover, the method is much more complex than its competitors.


Are Direct Links Necessary in RVFL NNs for Regression?

A random vector functional link network (RVFL) is widely used as a unive...

A Constructive Approach for Data-Driven Randomized Learning of Feedforward Neural Networks

Feedforward neural networks with random hidden nodes suffer from a probl...

Data-Driven Randomized Learning of Feedforward Neural Networks

Randomized methods of neural network learning suffer from a problem with...

Towards Shockingly Easy Structured Classification: A Search-based Probabilistic Online Learning Framework

There are two major approaches for structured classification. One is the...

Biologically Inspired Feedforward Supervised Learning for Deep Self-Organizing Map Networks

In this study, we propose a novel deep neural network and its supervised...

Please sign up or login with your details

Forgot password? Click here to reset