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 16 of 16 for “"Neural networks (Computer science) -- Mathematical models"”.

  1. Mosaic solutions and spatial entropy for a class of neural network models

    Includes bibliographical references (pages 42-44).

    colo-mines Repository record for Mosaic solutions and spatial entropy for a class of neural network models (opens in a new tab)

  2. Efficient multiprocessor scheduling by mean field theory neural networks

    … method based on Mean Field Theory (MFT) Neural Networks to solve the Task Scheduling problem. The MFT algorithm combines characteristics of the Simulated Annealing (SA) algorithm and the Hopfield neural network. MFT exhibits rapid convergence and at the same time it preserves the solution …

    njit Repository record for Efficient multiprocessor scheduling by mean field theory neural networks (opens in a new tab)

  3. Chemical Reaction Network Control Systems for Agent-Based Foraging Tasks

    Chemical reaction networks are an unconventional computing medium that could benefit from the ability to form basic control systems. In this work, we demonstrate the functionality of a chemical control system by evaluating classic genetic algorithm problems: Koza's Santa Fe trail, Jefferson's John …

    portland-state Repository record for Chemical Reaction Network Control Systems for Agent-Based Foraging Tasks (opens in a new tab)

  4. Function Approximation Guarantees for a Shallow Neural Network Trained by Gradient Flow

    … the same number of learnable parameters, deep neural networks can approximate richer classes of functions, with better accuracy than classical methods. The bulk of approximation theory results though, are only concerned with the infimum error for all possible parameterizations of a given …

    ucf Repository record for Function Approximation Guarantees for a Shallow Neural Network Trained by Gradient Flow (opens in a new tab)

  5. Towards Robust Deep Learning: Label Noise Modeling, Algorithms, and Applications

    … a tensor factorization–based methodology that models the noise transition process as an instance-dependent decomposition. We also utilize low-rank block-term structures to capture class-specific and instance-specific correlations. Moreover, we include a robust loss function and rank …

    ucf Repository record for Towards Robust Deep Learning: Label Noise Modeling, Algorithms, and Applications (opens in a new tab)

  6. Adversarial Attacks, Coarse Robustness, and Dataless Neural Networks: Novel Techniques for Improved Classification and Combinatorial Optimization

    Neural networks (NN) have become a central component in most machine learning systems. However, studies have shown that these models are not robust against adversarial attacks. As such, in this dissertation, we explore four directions. In the first direction, we investigate adversarial attacks on …

    ucf Repository record for Adversarial Attacks, Coarse Robustness, and Dataless Neural Networks: Novel Techniques for Improved Classification and Combinatorial Optimization (opens in a new tab)

  7. Maximum Probability Framework and Digital Probabilistic Models

    … the underlying theories of probabilistic models for application in large scale machine learning tasks. First, we introduce the maximum probability theorem and its consequences. We present a theoretical framework of probabilistic learning derived from the Maximum Probability (MP) Theorem. …

    ucf Repository record for Maximum Probability Framework and Digital Probabilistic Models (opens in a new tab)

  8. Hybrid Physics-informed Neural Networks for Dynamical Systems

    … differential equations through recurrent neural networks using Python. We leveraged modern machine learning frameworks, such as TensorFlow and Keras. Besides offering basic models capabilities (such as multilayer perceptrons and recurrent neural networks) and optimization methods, these …

    ucf Repository record for Hybrid Physics-informed Neural Networks for Dynamical Systems (opens in a new tab)

  9. Implication of Manifold Assumption in Deep Learning Models for Computer Vision Applications

    The Deep Neural Networks (DNN) have become the main contributor in the field of machine learning (ML). Specifically in the computer vision (CV), there are applications like image and video classification, object detection and tracking, instance segmentation and visual question answering, image and …

    ucf Repository record for Implication of Manifold Assumption in Deep Learning Models for Computer Vision Applications (opens in a new tab)

  10. Self-organizing neural network implemented in analog circuitry requires supervisional, scaling and parametric optimization attributable to 1/f noise

    … thesis describes the utilization of an analog computer for the purely analog electronic implementation of an unsupervised neural network. Results indicate that the algorithmic principles embodied 1n the nonlinear ordinary differential equations of Grossberg's Outstar learning model are …

    ucf Repository record for Self-organizing neural network implemented in analog circuitry requires supervisional, scaling and parametric optimization attributable to 1/f noise (opens in a new tab)

  11. Dynamics of neural networks and disordered spin systems

    <p>I obtain a number of results for the dynamics of several disordered spin systems, of successively greater complexity. I commence with the generalised Hopfield model trained with an intensive number of patterns, where in the thermodynamic limit macroscopic, deterministic equations of motion can …

    oxford Repository record for Dynamics of neural networks and disordered spin systems (opens in a new tab)

  12. Do determinístico ao aprendizado de máquina: uma nova abordagem para estimar a turbulência atmosférica

    … of uncertainty in numerical weather and climate models. In this work, the use of artificial neural networks of the Multi-Layer Perceptron type is proposed as surrogate models to emulate the Holtslag–Boville turbulence parameterization scheme in the Brazilian one-dimensional model BAM-1D. The …

    brazil-uerj Repository record for Do determinístico ao aprendizado de máquina: uma nova abordagem para estimar a turbulência atmosférica (opens in a new tab)

  13. Multi-scale nonlinear constitutive models using artificial neural networks

    … approach for nonlinear multi-scale constitutive models using artificial neural networks (ANNs). Three ANN classes are proposed to characterize the nonlinear multi-axial stress-strain behavior of metallic, polymeric, and fiber reinforced polymeric (FRP) materials, respectively. Load-displacement …

    gatech Repository record for Multi-scale nonlinear constitutive models using artificial neural networks (opens in a new tab)