Prediction of toxicity using a novel RBF neural network training methodology

2005 ◽  
Vol 12 (3) ◽  
pp. 297-305 ◽  
Author(s):  
Georgia Melagraki ◽  
Antreas Afantitis ◽  
Kalliopi Makridima ◽  
Haralambos Sarimveis ◽  
Olga Igglessi-Markopoulou
Keyword(s):  
Neural Network ◽  
Rbf Neural Network ◽  
Neural Network Training ◽  
Training Methodology ◽  
Network Training

A Novel RBF Neural Network Training Methodology to Predict Toxicity to Vibrio Fischeri

2006 ◽  
Vol 10 (2) ◽  
pp. 213-221 ◽  
Author(s):  
Georgia Melagraki ◽  
Antreas Afantitis ◽  
Haralambos Sarimveis ◽  
Olga Igglessi-Markopoulou ◽  
Alex Alexandridis
Keyword(s):  
Neural Network ◽  
Vibrio Fischeri ◽  
Rbf Neural Network ◽  
Neural Network Training ◽  
Training Methodology ◽  
Network Training

scholarly journals Improving the Classification Efficiency of an ANN Utilizing a New Training Methodology

Informatics ◽  
2018 ◽  
Vol 6 (1) ◽  
pp. 1 ◽  
Author(s):  
Ioannis Livieris
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Predictive Models ◽  
Numerical Experiments ◽  
Neural Network Training ◽  
Training Algorithm ◽  
New Approach ◽  
Training Methodology ◽  
Network Training ◽  
Classification Efficiency

In this work, a new approach for training artificial neural networks is presented which utilises techniques for solving the constraint optimisation problem. More specifically, this study converts the training of a neural network into a constraint optimisation problem. Furthermore, we propose a new neural network training algorithm based on the L-BFGS-B method. Our numerical experiments illustrate the classification efficiency of the proposed algorithm and of our proposed methodology, leading to more efficient, stable and robust predictive models.

scholarly journals A Geometric Perspective on Information Plane Analysis

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 711
Author(s):  
Mina Basirat ◽  
Bernhard C. Geiger ◽  
Peter M. Roth
Keyword(s):  
Neural Network ◽  
Mutual Information ◽  
Geometric Interpretation ◽  
Neural Network Training ◽  
Neural Network Learning ◽  
Network Learning ◽  
Plane Analysis ◽  
Network Training ◽  
Hidden Layer ◽  
The Impact

Information plane analysis, describing the mutual information between the input and a hidden layer and between a hidden layer and the target over time, has recently been proposed to analyze the training of neural networks. Since the activations of a hidden layer are typically continuous-valued, this mutual information cannot be computed analytically and must thus be estimated, resulting in apparently inconsistent or even contradicting results in the literature. The goal of this paper is to demonstrate how information plane analysis can still be a valuable tool for analyzing neural network training. To this end, we complement the prevailing binning estimator for mutual information with a geometric interpretation. With this geometric interpretation in mind, we evaluate the impact of regularization and interpret phenomena such as underfitting and overfitting. In addition, we investigate neural network learning in the presence of noisy data and noisy labels.

Sign in / Sign up

Export Citation Format

Share Document