Výsledky vyhledávání - "KASUMBA, HENRY"

Report

Efficient Saddle Point Evasion and Local Minima Escape in High-Dimensional Non-Convex Optimization

This paper addresses the challenges of high-dimensional non-convex optimization, particularly the inefficiencies caused by saddle points. The authors propose several techniques for detecting, evading, and optimizing in the presence of these saddle po

Externí odkaz: http://arxiv.org/abs/2409.12604

Zobrazit plný text záznamu

Report

Some Results on Neural Network Stability, Consistency, and Convergence: Insights into Non-IID Data, High-Dimensional Settings, and Physics-Informed Neural Networks

Autor: Katende, Ronald, Kasumba, Henry, Kakuba, Godwin, Mango, John M.

This paper addresses critical challenges in machine learning, particularly the stability, consistency, and convergence of neural networks under non-IID data, distribution shifts, and high-dimensional settings. We provide new theoretical results on un

Externí odkaz: http://arxiv.org/abs/2409.05030

Zobrazit plný text záznamu

Report

The time fractional order derivative for multi-class AR model

Autor: Nanyondo, Josephine, Mugisha, Joseph Y. T., Kasumba, Henry

In this paper, a multi-class Aw-Rascle \textrm{(AR)} model with time fractional order derivative is presented. The conservative form of the proposed model is considered for the natural extension and generalization of equations involved. The fractiona

Externí odkaz: http://arxiv.org/abs/2405.09888

Zobrazit plný text záznamu

Report

Analysis of Heterogeneous Vehicular Traffic: Using Proportional Densities

Autor: Josephine, Nanyondo, Kasumba, Henry

An extended multi-class Aw-Rascle (AR) model with pressure term described as a function of area occupancy defined in form of proportional densities is presented. Two vehicle classes that is; cars and motorcycles are considered based on an assumption

Externí odkaz: http://arxiv.org/abs/2306.00692

Zobrazit plný text záznamu

Report

Eigenvector Centrality and Uniform Dominant Eigenvalue of Graph Components

Autor: Anguzu, Collins, Engström, Christopher, Mango, John Magero, Kasumba, Henry, Silvestrov, Sergei, Abola, Benard

Eigenvector centrality is one of the outstanding measures of central tendency in graph theory. In this paper we consider the problem of calculating eigenvector centrality of graph partitioned into components and how this partitioning can be used. Two

Externí odkaz: http://arxiv.org/abs/2107.09137

Zobrazit plný text záznamu