A Cognitive Framework for Core Language Understanding and its Computational Implementation
International Journal of Cognitive Informatics and Natural Intelligence
| Hi-index | 0.00 |
Stability and plasticity in learning systems are both equally essential, but achieving stability and plasticity simultaneously is difficult. Adaptive resonance theory (ART) neural networks are known for their plastic and stable learning of categories, hence providing an answer to the so called stability-plasticity dilemma. However, it has been demonstrated recently that contrary to general belief, ART stability is not possible with infinite streaming data. In this paper, we present an improved stabilization strategy for ART neural networks that does not suffer from this problem and that produces a soft-clustering solution as a positive side effect. Experimental results in a task of text clustering demonstrate that the new stabilization strategy works well, but with a slight loss in clustering quality compared to the traditional approach. For real-life intelligent applications in which infinite streaming data is generated, the stable and soft-clustering solution obtained with our approach more than outweighs the small loss in quality.