We propose a fuzzy clustering method that relies on an artificial neural network scheme based on an encoder-decoder architecture with autoassociative training. The encoder is designed to implement a set of competing fuzzy membership functions which are trained to fit the data so that the decoder reconstruction error is minimized. In order to enforce a suitable cluster partitioning and membership distribution, the critical factor of the method is an entropy based regularization that constrains the encoder outputs. We present the results of our approach applied to synthetic data sets featuring both disjoin and intersecting compact clusters.