The majority of neural models for pattern recognition have fixed architecture during training. A typical consequence is non-optimal and often too large networks. In this paper we propose a Self-structuring Hidden Control (SHC) neural model for pattern recognition, which establishes a near optimal architecture during training. We typically achieve a significant network architecture reduction in terms of the number of hidden Processing Elements (PE). The SHC model combines self-structuring architecture generation with non-linear prediction and hidden Markov modelling. The paper presents a theorem for self-structuring neural models stating that these models are universal approximators and thus relevant for real-world pattern recognition. Using SHC models containing as few as five hidden PES each for an isolated word recognition task resulted in a recognition rate of 98.4%. SHC models can furthermore be applied to continuous speech recognition.
|Title of host publication||Neural Networks for Signal Processing II : Proceedings of the 1992 IEEE-SP Workshop|
|Publication status||Published - 1992|
|Event||1992 IEEE Workshop on Neural Networks for Signal Processing - Hotel Marielyst, Helsingoer, Denmark|
Duration: 31 Aug 1992 → 2 Sep 1992
|Workshop||1992 IEEE Workshop on Neural Networks for Signal Processing|
|Period||31/08/1992 → 02/09/1992|