English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Feedforward neural networks are widely used as universal predictive models tofit data distribution. Common gradient-based learning, however, suffers frommany drawbacks making the training process ineffective and time-consuming.Alternative randomized learning does not use gradients but selects hidden nodeparameters randomly. This makes the training process extremely fast. However,the problem in randomized learning is how to determine the random parameters. Arecently 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 somedrawbacks, we show how to improve it. We propose a learning method ofautoencoders that controls the produced random weights. We also propose how todetermine the biases of hidden nodes. We empirically compare autoencoder basedlearning with other randomized learning methods proposed recently forregression and find that despite the proposed improvement of the autoencoderbased learning, it does not outperform its competitors in fitting accuracy.Moreover, the method is much more complex than its competitors.

Autoencoder based Randomized Learning of Feedforward Neural Networks for Regression