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"”.
-
Mosaic solutions and spatial entropy for a class of neural network models
Includes bibliographical references (pages 42-44).
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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. …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …