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

arXiv:2404.03992v1 Announce Type: new
Abstract: 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 …

abstract arxiv cs.ai cs.cv cs.lg cs.ne deep learning deep learning performance dice dropout impact interactions networks neural networks noise overfitting paper performance randomization randomness study type