Selective Memory Recursive Least Squares: Uniformly Allocated Approximation Capabilities of RBF Neural Networks in Real-Time Learning. (arXiv:2211.07909v1 [eess.SY])

When performing real-time learning tasks, the radial basis function neural
network (RBFNN) is expected to make full use of the training samples such that
its learning accuracy and generalization capability are guaranteed. Since the
approximation capability of the RBFNN is finite, training methods with
forgetting mechanisms such as the forgetting factor recursive least squares
(FFRLS) and stochastic gradient descent (SGD) methods are widely used to
maintain the learning ability of the RBFNN to new knowledge. However, with the
forgetting mechanisms, …

approximation arxiv least memory networks neural networks real-time recursive squares