An improved architecture for Probabilistic Neural Networks

The paper proposes an improved architecture for Probabilistic Neural Networks (IAPNN) with an aggregation function based on f-mean of training patterns. The improved architecture has reduced number of layers and that reduces the computational complexity. Performance of the proposed model was compared with the traditional Probabilistic Neural Networks (PNN) and Learning Vector Quantization based Probabilistic Neural Network on various benchmark datasets. It is observed from the performance evaluation on various benchmark datasets that IAPNN outperforms in terms of classification accuracy. The redeeming feature of IAPNN is that the computational time for classification is drastically reduced.