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 8 of 8 for “"Auto-differentiation"”.

  1. Hyper-gates Framework for Straight-line Programs and Their Applications in Nonlinear Algebra

    … homotopy continuation. These solvers rely on automatic (auto) differentiation, and since auto differentiation can be represented as an SLP, it is of great interest to represent the entire solver as an SLP for hardware acceleration. This thesis introduces HGates.m2, a framework that expands on …

    gatech Repository record for Hyper-gates Framework for Straight-line Programs and Their Applications in Nonlinear Algebra (opens in a new tab)

  2. Open Mic with LISA: Intermediate-Mass Black Holes and Double White Dwarfs

    … Fisher matrix calculations which makes use of auto-differentiation. In this thesis we focus on papers [1–4] where the author made major contributions. To a lesser extent, the author also contributed to papers [5–7] over the course of the PhD program.

    jhu Repository record for Open Mic with LISA: Intermediate-Mass Black Holes and Double White Dwarfs (opens in a new tab)

  3. Robust NMPC of Large-Scale Systems and Surrogate Embedding Strategies for NMPC

    … the optimization framework, leveraging the auto differentiation (AD) of algebraic modelling languages (AMLs) to evaluate the derivatives. Alternatively, the surrogate can be evaluated externally from the optimization framework, using the efficient AD of ML environments. Physics-informed NNs …

    waterloo Repository record for Robust NMPC of Large-Scale Systems and Surrogate Embedding Strategies for NMPC (opens in a new tab)

  4. Methods for mitigating non-idealities in analog-domain compute accelerators

    … Unlike conventional interpolation, DI support auto-differentiation for compatibility with a leading deep learning library. DI is compared to the regression methods explored in Chapter 3 and demonstrates low loss with reduced compute overhead. This method is applied to model the undesired …

    texas Repository record for Methods for mitigating non-idealities in analog-domain compute accelerators (opens in a new tab)

  5. Physics Informed Deep Learning Application In High-Dimensional Groundwater Inverse Modeling Of Hydraulic Tomography

    … efficiently and accurately. Importantly, its auto-differentiation eliminates the need for iterative forward simulations as seen in traditional optimization methods. The combined FNO-RGA model excels in accuracy, efficiency, and adaptability when employed for inverse modeling of non-smooth …

    gatech Repository record for Physics Informed Deep Learning Application In High-Dimensional Groundwater Inverse Modeling Of Hydraulic Tomography (opens in a new tab)

  6. Deep Learning for Studying Materials Stability and Solving Thermodynamically Consistent PDES With Dynamic Boundary Conditions in Arbitrary Domains

    … improve the performance. We present the use of auto-differentiation techniques to easily and precisely evaluate surface differential operators associated with dynamic boundary conditions, making it applicable to arbitrary smooth geometries. The efficacy of our methodology is demonstrated through …

    south-carolina Repository record for Deep Learning for Studying Materials Stability and Solving Thermodynamically Consistent PDES With Dynamic Boundary Conditions in Arbitrary Domains (opens in a new tab)

  7. Deep multi-agent reinforcement learning

    … of real world problems, such as the control of autonomous vehicles and drones, packet delivery, and many others consists of a number of agents that need to take actions based on local observations and can thus be formulated in the multi-agent reinforcement learning (MARL) setting. Furthermore, …

    oxford Repository record for Deep multi-agent reinforcement learning (opens in a new tab)

  8. Ο ρόλος των αυτόματων ερεθισμάτων δράσης στην αντιμετώπιση της στερεοτυπικής λεκτικής συμπεριφοράς σε παιδιά εντός και εκτός του αυτιστικού φάσματος

    … novel stimuli without further prompting. Digital automatization freed practitioners from otherwise unmanageable procedural demands. In the second experiment, five boys, four with high-functioning Autism Spectrum Disorder (ASD) and one with neurotypical development, were exposed to a differential …

    greece Repository record for Ο ρόλος των αυτόματων ερεθισμάτων δράσης στην αντιμετώπιση της στερεοτυπικής λεκτικής συμπεριφοράς σε παιδιά εντός και εκτός του αυτιστικού φάσματος (opens in a new tab)