Comparison between real-time learning capabilities of the IDS method and Radial Basis Function Networks

The ink drop spread (IDS) method is a modeling technique developed by algorithmically mimicking the information-handling processes of the human brain, and it has been proposed as a new soft computing paradigm. This study investigates the real-time performance of the IDS method. Radial basis function networks (RBFNs) are artificial neural networks that are characterized by the speed of learning. This study compares the real-time learning capability of the IDS method with that of RBFNs. In the approximation of five different functions used as a benchmark, the IDS method exhibits stable and fast convergence in terms of the learning time and the number of training examples used. This study also presents an effective approach to enhance the real-time performance of the IDS method.