Open Access
A Heterogeneous Ensemble Network Using Machine Learning Techniques
Tarik A. Rashid
- 01 Jan 2009
TL;DR: A heterogeneous ensemble network that can combine the outputs of several networks of different types is introduced that shows the ability to avoid an under or over estimated prediction of electricity load.
read more
Abstract: Summary The process of the ensemble network can be defined as grouping several networks where each independent network from that group is trained independently and then outputs are combined to obtain the overall output. This is called ensemble network. Usually, the output of ensemble network is often more accurate than outputs of any independent network. The ensemble network can be either homogenous or heterogeneous. The homogenous ensemble network obtains the overall output from different independent network structures of the same type, whereas the heterogeneous ensemble network obtains the overall output from identical independent network structures, but each independent network is trained with different training sets. In this paper, we introduce a heterogeneous ensemble network that can combine the outputs of several networks of different types. Heterogeneous ensemble network is created from recurrent neural network namely is called multi context recurrent neural network, variants of this network is used with variants functions of support vector machines to improve accuracy of the prediction task. The ensemble network is applied here to solve the problem of forecasting for electricity load energy. The network shows the ability to avoid an under or over estimated prediction of electricity load.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Evolution of heterogeneous ensembles through dynamic particle swarm optimization for video-based face recognition
TL;DR: Simulation results indicate the DPSO strategy provides an efficient way to evolve ensembles of FAM networks in an AMCS using reference ensemble-based and batch learning techniques, but requires significantly lower computational complexity than assessing diversity among classifiers in the feature or decision spaces.
37
Dynamic multi-objective evolution of classifier ensembles for video face recognition
Jean-Francois Connolly,Eric Granger,Robert Sabourin +2 more
- 01 Jun 2013
TL;DR: An incremental learning strategy based on particle swarm optimization (PSO) is proposed to efficiently evolve heterogeneous classifier ensembles in response to new reference data and results indicate that the proposed strategy provides a level of accuracy similar to that of using mono-objective optimization and reference face recognition systems.
Improving the Identification Performance of an Industrial Process Using Multiple Neural Networks
E. Shafiei,H. Jazayeri-Rad +1 more
TL;DR: This paper uses multip le neural networks (MNNs) for modelling a continuous stirred tank reactor (CSTR) and compares the results against the SNN model, showing that the use of MNNs proves the model performance.
A multi hidden recurrent neural network with a modified grey wolf optimizer
TL;DR: This proposed system would improve instruction by the faculty and enhance the students’ learning experiences and show that a modified recurrent neural network with an adapted Grey Wolf Optimizer has the best accuracy when compared with other models.
References
Bagging predictors
Leo Breiman
- 01 Aug 1996
TL;DR: Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy.
Neural network ensembles
Lars Kai Hansen,Peter Salamon +1 more
TL;DR: It is shown that the remaining residual generalization error can be reduced by invoking ensembles of similar networks, which helps improve the performance and training of neural networks for classification.
Neural network with ensembles
Ernst Kussul,Oleksandr Makeyev,Tatiana Baidyk,Daniel Calderon Reyes +3 more
- 18 Jul 2010
TL;DR: This paper proposes the use of the neural networks with ensembles for pattern recognition problems that demands many thousands of classes to be recognized and gives a short description of this type of neural network and its storage capacity.
1.3K
•Book
Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems
Amanda J. C. Sharkey
- 15 Apr 1999
TL;DR: This volume, written by leading researchers, presents methods of combining neural nets to improve their performance and suggests ways to improve the quality of these nets.
630
CIXL2: a crossover operator for evolutionary algorithms based on population features
TL;DR: A crossover operator for evolutionary algorithms with real values that is based on the statistical theory of population distributions that takes into account the localization and dispersion features of the best individuals of the population with the objective that these features would be inherited by the offspring.