Naslov
Empirical Evaluation of the Effect of Optimization and Regularization Techniques on the Generalization Performance of Deep Convolutional Neural Network

Autori
Marin, Ivana ; Kuzmanić Skelin, Ana ; Grujić, Tamara

Izvornik
Applied Sciences-Basel (2076-3417) 10 (2020), 21; 7817, 30

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
neural networks ; optimization ; regularization ; overfitting ; model generalization ; image processing

Sažetak
The main goal of any classification or regression task is to obtain a model that will generalize well on new, previously unseen data. Due to the recent rise of deep learning and many state-of-the-art results obtained with deep models, deep learning architectures have become one of the most used model architectures nowadays. To generalize well, a deep model needs to learn the training data well without overfitting. The latter implies a correlation of deep model optimization and regularization with generalization performance. In this work, we explore the effect of the used optimization algorithm and regularization techniques on the final generalization performance of the model with convolutional neural network (CNN) architecture widely used in the field of computer vision. We give a detailed overview of optimization and regularization techniques with a comparative analysis of their performance with three CNNs on the CIFAR-10 and Fashion- MNIST image datasets.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA