Search research articles

Search research articles

Related Experiment Videos

An information theoretic approach for combining neural network process models.

D V. Sridhar¹, E B. Bartlett, R C. Seagrave

¹Department of Chemical Engineering, Iowa State University, Ames, IA, USA

Neural Networks : the Official Journal of the International Neural Network Society

|March 29, 2003

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same journal

A practical design of backdoor trigger under frequency-based orthogonality constraints.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

EEG fine-grained visual semantic decoding via a multimodal framework.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Collaborative-adversarial jailbreaking: A propagation-aware attack framework for multi-agent code generation systems.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Theoretical analysis of the denoising autoencoder using Tweedie's formula.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Frequency-based cross-attention fusion network for RGB-D salient object detection.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

HTNet: A self-supervised heterogeneous triple network for multi-modal data.

Neural networks : the official journal of the International Neural Network Society·2026

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

This study introduces an information theoretic stacking (ITS) algorithm to combine multiple neural network models. ITS enhances chemical process modeling by effectively integrating diverse models, outperforming single models and linear combinations.

Area of Science:

Chemical Engineering
Artificial Intelligence
Computational Science

Background:

Neural network modeling in chemical engineering often relies on single, optimal models, potentially overlooking valuable information from other models.
Existing stacked neural networks (SNNs) use linear combinations, limiting their ability to incorporate non-linearly related model outputs.

Purpose of the Study:

To propose a novel information theoretic stacking (ITS) algorithm for combining neural network models.
To develop SNNs that can integrate useful models regardless of their relationship to the output.
To demonstrate the improved performance of ITS-based SNNs in chemical process modeling.

Main Methods:

Development of the information theoretic stacking (ITS) algorithm.
Integration of multiple neural networks into SNNs using the ITS algorithm.

Related Experiment Videos

Application and validation of ITS-based SNNs on dynamic process modeling problems.

Main Results:

The ITS algorithm effectively identifies and combines useful neural network models, irrespective of linear or non-linear relationships.
SNNs developed using ITS show significantly improved performance compared to single models.
ITS-based SNNs outperform SNNs that rely solely on linear combinations of models.

Conclusions:

The proposed ITS algorithm offers a powerful method for enhancing neural network model ensembles in chemical engineering.
ITS-based SNNs provide superior predictive accuracy and information extraction compared to traditional approaches.
This approach advances the field of neural network applications in complex process modeling.