Automatic Pattern Recognition: A Study of the Probability of Error
IEEE Transactions on Pattern Analysis and Machine Intelligence
Connectionist learning procedures
Machine learning: paradigms and methods
Applications of error back-propagation to phonetic classification
Advances in neural information processing systems 1
Links Between Markov Models and Multilayer Perceptrons
IEEE Transactions on Pattern Analysis and Machine Intelligence
Maximum likelihood competitive learning
Advances in neural information processing systems 2
Soft competitive adaptation: neural network learning algorithms based on fitting statistical mixtures
Task Decomposition Through Competition in a Modular Connectionist
Task Decomposition Through Competition in a Modular Connectionist
A time delay neural network architecture for speech recognition
A time delay neural network architecture for speech recognition
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Evolutionary Learning of Modular Neural Networks withGenetic Programming
Applied Intelligence
A Connectionist-Symbolic Approach to Modeling Agent Behavior: Neural Networks Grouped by Contexts
CONTEXT '01 Proceedings of the Third International and Interdisciplinary Conference on Modeling and Using Context
Decision-tree instance-space decomposition with grouped gain-ratio
Information Sciences: an International Journal
Classifier ensembles: Select real-world applications
Information Fusion
Artificial Intelligence Review
A hybrid learning approach for better recognition of visual objects
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
A framework for selection and fusion of pattern classifiers in multimedia recognition
Pattern Recognition Letters
Embedded local feature selection within mixture of experts
Information Sciences: an International Journal
Hi-index | 0.14 |
The authors present the Meta-Pi network, a multinetwork connectionist classifier that forms distributed low-level knowledge representations for robust pattern recognition, given random feature vectors generated by multiple statistically distinct sources. They illustrate how the Meta-Pi paradigm implements an adaptive Bayesian maximum a posteriori classifier. They also demonstrate its performance in the context of multispeaker phoneme recognition in which the Meta-Pi superstructure combines speaker-dependent time-delay neural network (TDNN) modules to perform multispeaker /b,d,g/ phoneme recognition with speaker-dependent error rates of 2%. Finally, the authors apply the Meta-Pi architecture to a limited source-independent recognition task, illustrating its discrimination of a novel source. They demonstrate that it can adapt to the novel source (speaker), given five adaptation examples of each of the three phonemes.