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

In this work, a non-gradient descent learning (NGDL) scheme was proposed fordeep feedforward neural networks (DNN). It is known that an autoencoder can beused as the building blocks of the multi-layer perceptron (MLP) DNN, the MLP istaken as an example to illustrate the proposed scheme of pseudoinverse learningalgorithm for autoencoder (PILAE) in this paper. The PILAE with low rankapproximation is a NGDL algorithm, and the encoder weight matrix is set to bethe low rank approximation of the pseudoinverse of the input matrix, while thedecoder weight matrix is calculated by the pseudoinverse learning algorithm. Itis worth to note that only very few network structure hyper-parameters need tobe tuned compared with classical gradient descent learning algorithm. Hence,the proposed algorithm could be regarded as a quasi-automated trainingalgorithm which could be utilized in automated machine learning field. Theexperimental results show that the proposed learning scheme for DNN couldachieve better performance on considering the tradeoff between trainingefficiency and classification accuracy.

PILAE: A Non-gradient Descent Learning Scheme for Deep Feedforward Neural Networks