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 recent years, deep learning based on artificial neural network (ANN) hasachieved great success in pattern recognition. However, there is no clearunderstanding of such neural computational models. In this paper, we try tounravel "black-box" structure of Ann model from network flow. Specifically, weconsider the feed forward Ann as a network flow model, which consists of manydirectional class-pathways. Each class-pathway encodes one class. Theclass-pathway of a class is obtained by connecting the activated neural nodesin each layer from input to output, where activation value of neural node(node-value) is defined by the weights of each layer in a trainedANN-classifier. From the perspective of the class-pathway, training anANN-classifier can be regarded as the formulation process of class-pathways ofdifferent classes. By analyzing the the distances of each two class-pathways ina trained ANN-classifiers, we try to answer the questions, why the classifierperforms so? At last, from the neural encodes view, we define the importance ofeach neural node through the class-pathways, which is helpful to optimize thestructure of a classifier. Experiments for two types of ANN model includingmulti-layer MLP and CNN verify that the network flow based on class-pathway isa reasonable explanation for ANN models.

Understanding the Feedforward Artificial Neural Network Model From the Perspective of Network Flow