Stochastic Configuration Networks: Fundamentals and Algorithms
This work addresses the need for efficient and automated neural network design in machine learning, though it is incremental as it builds on existing randomized methods for single-layer feed-forward networks.
The paper tackles the problem of designing randomized neural networks by introducing Stochastic Configuration Networks (SCNs), which incrementally assign hidden node parameters with a supervisory mechanism and analytically compute output weights, achieving fast learning and sound generalization with less human intervention.
This paper contributes to a development of randomized methods for neural networks. The proposed learner model is generated incrementally by stochastic configuration (SC) algorithms, termed as Stochastic Configuration Networks (SCNs). In contrast to the existing randomised learning algorithms for single layer feed-forward neural networks (SLFNNs), we randomly assign the input weights and biases of the hidden nodes in the light of a supervisory mechanism, and the output weights are analytically evaluated in either constructive or selective manner. As fundamentals of SCN-based data modelling techniques, we establish some theoretical results on the universal approximation property. Three versions of SC algorithms are presented for regression problems (applicable for classification problems as well) in this work. Simulation results concerning both function approximation and real world data regression indicate some remarkable merits of our proposed SCNs in terms of less human intervention on the network size setting, the scope adaptation of random parameters, fast learning and sound generalization.