Fast Genetic Algorithm for feature selection -- A qualitative approximation approach

no code implementations • 5 Apr 2024 • Mohammed Ghaith Altarabichi, Sławomir Nowaczyk, Sepideh Pashami, Peyman Sheikholharam Mashhadi

In this paper, we propose a two-stage surrogate-assisted evolutionary approach to address the computational issues arising from using Genetic Algorithm (GA) for feature selection in a wrapper setting for large datasets.

Evolutionary Algorithms feature selection

Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks

no code implementations • 5 Apr 2024 • Mohammed Ghaith Altarabichi, Sławomir Nowaczyk, Sepideh Pashami, Peyman Sheikholharam Mashhadi, Julia Handl

This paper investigates how various randomization techniques impact Deep Neural Networks (DNNs).

Data Augmentation Hyperparameter Optimization

Learning Causal Mechanisms through Orthogonal Neural Networks

1 code implementation • 5 Jun 2023 • Peyman Sheikholharam Mashhadi, Slawomir Nowaczyk

Addressing this crucial discrepancy between human and machine intelligence is an important challenge for pattern recognition systems.