We consider the task of acoustic system identification, where the input signal undergoes a memoryless nonlinear transformation before convolving with an unknown linear system. We...
Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
Gaussian Process prior models, as used in Bayesian non-parametric statistical models methodology are applied to implement a nonlinear adaptive control law. The expected value of a...
Capturing dependencies in images in an unsupervised manner is important for many image processing applications. We propose a new method for capturing nonlinear dependencies in ima...
— This paper reports the analytical development and preliminary experimental evaluation of a class of exact nonlinear full state model-based observers for underwater vehicle navi...