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 6 of 6 for “"universal approximation"”.

  1. Universal approximation of input-output maps and dynamical systems by neural network architectures

    … maps having limited long-term memory, we prove universal approximation guarantees for temporal convolutional nets constructed using only a finite number of computation units which hold on an infinite-time horizon. We also provide quantitative estimates for the width and depth of the network …

    uiuc Repository record for Universal approximation of input-output maps and dynamical systems by neural network architectures (opens in a new tab)

  2. INVERSE APPROXIMATION THEORY OF RECURRENT MODELS FOR LEARNING SEQUENCES

    … memory decay pattern. Then we prove the universal approximation property for state-space models. A similar inverse approximation result is established for state-space models, indicating that despite their high efficiency, changing the method of incorporating nonlinear activation fails to …

    nus Repository record for INVERSE APPROXIMATION THEORY OF RECURRENT MODELS FOR LEARNING SEQUENCES (opens in a new tab)

  3. Autoregressive Neural Network Processes - Univariate, Multivariate and Cointegrated Models with Application to the German Automobile Industry

    … of nonlinearity. This idea is based on the universal approximation property of single hidden layer feedforward neural networks of Hornik (1993). Univariate Autoregressive Neural Network Processes (AR-NN) as well as Vector Autoregressive Neural Network Processes (VAR-NN) and Neural Network …

    passau-thes Repository record for Autoregressive Neural Network Processes - Univariate, Multivariate and Cointegrated Models with Application to the German Automobile Industry (opens in a new tab)

  4. A neural network computer model of the hydrodynamical flow in the River Medway estuary at its confluence with the River Thames

    … certain parameters. The models demonstrated good universal approximation capabilities when varying the imposed velocities, still water depths and friction coefficients. Apart from minor discrepancies in generated depth and velocity data at the precise juncture of the two rivers, the networks …

    london-metro Repository record for A neural network computer model of the hydrodynamical flow in the River Medway estuary at its confluence with the River Thames (opens in a new tab)

  5. Exploring Complex Problems in Fluid Dynamics: from CFD to Experiments Leveraging ML

    … conditions. This methodology, influenced by the universal approximation theorem for functionals, represents a significant advancement in addressing engineering challenges. In summary, these studies emphasize the role of ML a instrumental tool in advancing marine systems, driving them toward …

    mit Repository record for Exploring Complex Problems in Fluid Dynamics: from CFD to Experiments Leveraging ML (opens in a new tab)

  6. Choice Modeling and Assortment Optimization on the Transformer Model

    … which we call transformer choice models. The universal approximation property of the transformer network ensures that our model can approximate any discrete choice model, and thus it can capture irrationalities in choice behavior. We perform computational experiments with real data to verify …

    mit Repository record for Choice Modeling and Assortment Optimization on the Transformer Model (opens in a new tab)