Flexible Architecture of Self Organizing Maps for Changing Environments

Catastrophic Interference is a well known problem of Artificial Neural Networks (ANN) learning algorithms where the ANN forgets useful knowledge while learning from new data. Furthermore the structure of most neural models must be chosen in advance. In this paper we introduce an hybrid algorithm called Flexible Architecture of Self Organizing Maps (FASOM ) that overcomes the Catastrophic Interference and preserves the topology of Clustered data in changing environments. The model consists in K receptive fields of self organizing maps. Each Receptive Field projects high-dimensional data of the input space onto a neuron position in a low-dimensional output space grid by dynamically adapting its structure to a specific region of the input space. Furthermore the FASOM model automatically finds the number of maps and prototypes needed to successfully adapt to the data. The model has the ability to grow when it is learning new clusters, and it can gradually forgets when data is reduced in the receptive field. Finally we show the capabilities of our model with experimental results using Synthetic Sequential data sets and real world data obtained from a site that contains benchmark data.