Randomized Constructive Neural Network Based on Regularized Minimum Error Entropy

So far several types of random neural networks have been proposed in which optimal output weights are adjusted using the Mean Square Error (MSE) objective function. However, since many real-world phenomena do not follow a normal distribution, MSE-based methods act poorly in such cases. This paper presents a new single-layer random constructive neural network based on the regularized Minimum Error Entropy (MEE) objective function. The proposed method investigates the performance of MSE and MEE objective functions in combination using a regularization term to adjust the optimal output parameter for new nodes. Experimental results show that the proposed method performs well in the presence of both Gaussian and impulsive noise. Furthermore, due to the random assignment of the hidden layer parameters, the computational burden of the proposed method is reduced. Incremental constructive architecture of the proposed network helps optimize non-convex objective functions to achieve the desired performance. Computational comparisons indicate the superior performance of our method with several synthetic and benchmark datasets.