USER: Unsupervised Structural Entropy-Based Robust Graph Neural Network

Robust Soft-Entropy Neural Network Trees

We present a new method for the induction of tree-structured recursive partitioning classifiers that use a neural network as the partitioning function at each node in the tree. Our technique is appropriate for pattern recognition tasks with many continuous inputs and a single multivalued nominal output. This paper presents two main contributions: 1) a novel objective function called soft entrop...

STRUCTURAL RESPONSE OBSERVER BASED ON ARTIFICIAL NEURAL NETWORK

Structural vibration control is one of the most important features in structural engineering. Real-time information about seismic resultant forces is required for deciding module of intelligent control systems. Evaluation of lateral forces during an earthquake is a complicated problem considering uncertainties of gravity loads amount and distribution and earthquake characteristics. An artificia...

Graph Based Convolutional Neural Network

In this paper we present a method for the application of Convolutional Neural Network (CNN) operators for use in domains which exhibit irregular spatial geometry by use of the spectral domain of a graph Laplacian, Figure 1. This allows learning of localized features in irregular domains by defining neighborhood relationships as edge weights between vertices in graph G. By formulating the domain...

Unsupervised Neural Network Learning

In this article, we review unsupervised neural network learning procedures which can be applied to the task of preprocessing raw data to extract useful features for subsequent classication. The learning algorithms reviewed here are grouped into three sections: informationpreserving methods, density estimation methods, and feature extraction methods. Each of these major sections concludes with a...

Low Entropy Coding with Unsupervised Neural Networks