A New Weight Initialization Method for the MLP with the BP inMulticlass Classification Problems
Neural Processing Letters
Handwritten Digit Recognition by a Mixture of Local PrincipalComponent Analysis
Neural Processing Letters
A fast learning algorithm for time-delay neural networks
Information Sciences—Applications: An International Journal
How to Automate Neural Net Based Learning
MLDM '01 Proceedings of the Second International Workshop on Machine Learning and Data Mining in Pattern Recognition
Ensembles of Learning Machines
WIRN VIETRI 2002 Proceedings of the 13th Italian Workshop on Neural Nets-Revised Papers
ACMD: A Practical Tool for Automatic Neural Net Based Learning
ISMDA '01 Proceedings of the Second International Symposium on Medical Data Analysis
Multiclassifier Systems: Back to the Future
MCS '02 Proceedings of the Third International Workshop on Multiple Classifier Systems
Effectiveness of Error Correcting Output Codes in Multiclass Learning Problems
MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
The Journal of Machine Learning Research
Experiments in speech recognition using a modular MLP architecture for acoustic modelling
Information Sciences—Informatics and Computer Science: An International Journal - Special issue: Spoken language analysis, modeling and recognition-statistical and adaptive connectionist approaches
A Hierarchical Classifier Using New Support Vector Machine
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Stochastic Organization of Output Codes in Multiclass Learning Problems
Neural Computation
Neural Networks - 2005 Special issue: IJCNN 2005
Improving Multiclass Pattern Recognition by the Combination of Two Strategies
IEEE Transactions on Pattern Analysis and Machine Intelligence
Ordered incremental training for GA-based classifiers
Pattern Recognition Letters
Hierarchical Incremental Class Learning with Reduced Pattern Training
Neural Processing Letters
Improving the classification of multiple disorders with problem decomposition
Journal of Biomedical Informatics
Multi-class pattern classification using neural networks
Pattern Recognition
A cooperative constructive method for neural networks for pattern recognition
Pattern Recognition
Intelligent Data Analysis
On Pairwise Naive Bayes Classifiers
ECML '07 Proceedings of the 18th European conference on Machine Learning
Cooperative Recurrent Neural Network for Multiclass Support Vector Machine Learning
ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
Computational Statistics & Data Analysis
Troika - An improved stacking schema for classification tasks
Information Sciences: an International Journal
Pattern Recognition Letters
Automatic fruit and vegetable classification from images
Computers and Electronics in Agriculture
Tree architecture pattern distributor: a task decomposition classification approach
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
A class decomposition approach for GA-based classifiers
Engineering Applications of Artificial Intelligence
Recursive hybrid decomposition with reduced pattern training
International Journal of Hybrid Intelligent Systems
A matrix modular SVM robust to imbalanced data for efficient visual concept detection
Proceedings of the international conference on Multimedia information retrieval
Parallel-series perceptrons for the simultaneous determination of odor classes and concentrations
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Resistive-type CVNS distributed neural networks with improved noise-to-signal ratio
IEEE Transactions on Circuits and Systems II: Express Briefs
A modular decision-tree architecture for better problem understanding
SEAL'10 Proceedings of the 8th international conference on Simulated evolution and learning
Cost-sensitive neural networks and editing techniques for imbalance problems
MCPR'10 Proceedings of the 2nd Mexican conference on Pattern recognition: Advances in pattern recognition
Resampling methods versus cost functions for training an MLP in the class imbalance context
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part I
A modular single-hidden-layer perceptron for letter recognition
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Fault detection of reactive ion etching using time series neural networks
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part III
Tissue classification using gene expression data and artificial neural network ensembles
ICIC'06 Proceedings of the 2006 international conference on Computational Intelligence and Bioinformatics - Volume Part III
One-against-all ensemble for multiclass pattern classification
Applied Soft Computing
Artificial Intelligence in Medicine
A first study on decomposition strategies with data with class noise using decision trees
HAIS'12 Proceedings of the 7th international conference on Hybrid Artificial Intelligent Systems - Volume Part II
Efficient pairwise classification using local cross off strategy
Canadian AI'12 Proceedings of the 25th Canadian conference on Advances in Artificial Intelligence
A subspace approach to error correcting output codes
Pattern Recognition Letters
Recursive Learning of Genetic Algorithms with Task Decomposition and Varied Rule Set
International Journal of Applied Evolutionary Computation
The use of artificial-intelligence-based ensembles for intrusion detection: a review
Applied Computational Intelligence and Soft Computing
A Fast Multiclass Classification Algorithm Based on Cooperative Clustering
Neural Processing Letters
International Journal of Knowledge-based and Intelligent Engineering Systems
Hi-index | 0.00 |
The rate of convergence of net output error is very low when training feedforward neural networks for multiclass problems using the backpropagation algorithm. While backpropagation will reduce the Euclidean distance between the actual and desired output vectors, the differences between some of the components of these vectors increase in the first iteration. Furthermore, the magnitudes of subsequent weight changes in each iteration are very small, so that many iterations are required to compensate for the increased error in some components in the initial iterations. Our approach is to use a modular network architecture, reducing a K-class problem to a set of K two-class problems, with a separately trained network for each of the simpler problems. Speedups of one order of magnitude have been obtained experimentally, and in some cases convergence was possible using the modular approach but not using a nonmodular network