Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 7 of 7 for “"Universal function approximation"”.

  1. Application of cascade-correlation neural networks to nonlinear system identification

    … algorithm, has been shown to be capable of universal function approximation which makes it applicable to a much wider range of problems than other nonlinear identification techniques. While these neural networks show great potential, they still suffer several drawbacks, such as slow …

    vt Repository record for Application of cascade-correlation neural networks to nonlinear system identification (opens in a new tab)

  2. Neural network based robust nonlinear control

    … dynamic systems with uncertainties due to their universal function approximation capabilities. This research explores the application of online neural networks for the design of model following controllers and for dynamic reoptimization of a Single Network Adaptive Critic (SNAC) optimal …

    must-thes Repository record for Neural network based robust nonlinear control (opens in a new tab)

  3. Probabilistic fuzzy logic framework in reinforcement learning for decision making

    … learning approach combined with the universal function approximation capability of fuzzy systems within a probabilistic fuzzy logic theory framework, where the information from the environment is not interpreted in a deterministic way as in classic approaches but rather, in a …

    salford Download PDF for Probabilistic fuzzy logic framework in reinforcement learning for decision making (opens in a new tab)

  4. A sensor fusion filter structure based on RBFNN aided Kalman filter in target positioning

    … integrates a Kalman filter with a radial basis function neural network (RBFNN) is presented in the thesis. Both extended Kalman filter (EKF) and converted measurement Kalman filter (CMKF) are implemented to verify the univesality of the system. RBFNN is chosen due to its universal function …

    chalmers Repository record for A sensor fusion filter structure based on RBFNN aided Kalman filter in target positioning (opens in a new tab)

  5. Development of adaptive fuzzy multiple models based control techniques for nonlinear systems

    … advantage of T-S models is that they have the ‘universal function approximation’ property, in the sense that they are able to approximate every smooth nonlinear function to any degree of accuracy in a convex compact region provided that sufficient fuzzy rules are available for the description of …

    greece Repository record for Development of adaptive fuzzy multiple models based control techniques for nonlinear systems (opens in a new tab)

  6. Representation and statistical properties of deep neural networks on structured data

    … the gap between theory and practice by studying function approximation and statistical theories of deep neural networks in exploitation of geometric structures in data. -- Function Approximation Theories on Low-dimensional Manifolds using Deep Neural Networks. We first develop an efficient …

    gatech Repository record for Representation and statistical properties of deep neural networks on structured data (opens in a new tab)

  7. Control of Uncertain Dynamical Systems with Spatial and Temporal Constraints

    … so-called generalized restricted potential functions by incorporating a system error-dependent learning rate in the adaptation process. The resulting control architecture ensures that the system error signal evolves in a user-defined compact set for all time without the requirement of the …

    usf Repository record for Control of Uncertain Dynamical Systems with Spatial and Temporal Constraints (opens in a new tab)