Approximation with Random Shallow ReLU Networks with Applications to Model Reference Adaptive Control

arXiv:2403.17142v1 Announce Type: cross
Abstract: Neural networks are regularly employed in adaptive control of nonlinear systems and related methods o reinforcement learning. A common architecture uses a neural network with a single hidden layer (i.e. a shallow network), in which the weights and biases are fixed in advance and only the output layer is trained. While classical results show that there exist neural networks of this type that can approximate arbitrary continuous functions over bounded regions, they are non-constructive, and …

abstract applications approximation architecture arxiv biases control cs.lg cs.sy eess.sy hidden layer math.oc network networks neural network neural networks random reference reinforcement reinforcement learning relu systems type weights and biases