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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Altarabichi, Mohammed Ghaith, Nowaczyk, Sławomir, Pashami, Sepideh, Mashhadi, Peyman Sheikholharam, Handl, Julia
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917630780112896
author Altarabichi, Mohammed Ghaith
Nowaczyk, Sławomir
Pashami, Sepideh
Mashhadi, Peyman Sheikholharam
Handl, Julia
author_facet Altarabichi, Mohammed Ghaith
Nowaczyk, Sławomir
Pashami, Sepideh
Mashhadi, Peyman Sheikholharam
Handl, Julia
contents This paper investigates how various randomization techniques impact Deep Neural Networks (DNNs). Randomization, like weight noise and dropout, aids in reducing overfitting and enhancing generalization, but their interactions are poorly understood. The study categorizes randomness techniques into four types and proposes new methods: adding noise to the loss function and random masking of gradient updates. Using Particle Swarm Optimizer (PSO) for hyperparameter optimization, it explores optimal configurations across MNIST, FASHION-MNIST, CIFAR10, and CIFAR100 datasets. Over 30,000 configurations are evaluated, revealing data augmentation and weight initialization randomness as main performance contributors. Correlation analysis shows different optimizers prefer distinct randomization types. The complete implementation and dataset are available on GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2404_03992
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks
Altarabichi, Mohammed Ghaith
Nowaczyk, Sławomir
Pashami, Sepideh
Mashhadi, Peyman Sheikholharam
Handl, Julia
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
This paper investigates how various randomization techniques impact Deep Neural Networks (DNNs). Randomization, like weight noise and dropout, aids in reducing overfitting and enhancing generalization, but their interactions are poorly understood. The study categorizes randomness techniques into four types and proposes new methods: adding noise to the loss function and random masking of gradient updates. Using Particle Swarm Optimizer (PSO) for hyperparameter optimization, it explores optimal configurations across MNIST, FASHION-MNIST, CIFAR10, and CIFAR100 datasets. Over 30,000 configurations are evaluated, revealing data augmentation and weight initialization randomness as main performance contributors. Correlation analysis shows different optimizers prefer distinct randomization types. The complete implementation and dataset are available on GitHub.
title Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Neural and Evolutionary Computing
url https://arxiv.org/abs/2404.03992