Reference Hub57
Preventing Model Overfitting and Underfitting in Convolutional Neural Networks

Preventing Model Overfitting and Underfitting in Convolutional Neural Networks

Andrei Dmitri Gavrilov, Alex Jordache, Maya Vasdani, Jack Deng
Copyright: © 2018 |Volume: 10 |Issue: 4 |Pages: 10
ISSN: 1942-9045|EISSN: 1942-9037|EISBN13: 9781522544050|DOI: 10.4018/IJSSCI.2018100102
Cite Article Cite Article

MLA

Gavrilov, Andrei Dmitri, et al. "Preventing Model Overfitting and Underfitting in Convolutional Neural Networks." IJSSCI vol.10, no.4 2018: pp.19-28. http://doi.org/10.4018/IJSSCI.2018100102

APA

Gavrilov, A. D., Jordache, A., Vasdani, M., & Deng, J. (2018). Preventing Model Overfitting and Underfitting in Convolutional Neural Networks. International Journal of Software Science and Computational Intelligence (IJSSCI), 10(4), 19-28. http://doi.org/10.4018/IJSSCI.2018100102

Chicago

Gavrilov, Andrei Dmitri, et al. "Preventing Model Overfitting and Underfitting in Convolutional Neural Networks," International Journal of Software Science and Computational Intelligence (IJSSCI) 10, no.4: 19-28. http://doi.org/10.4018/IJSSCI.2018100102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The current discourse in the machine learning domain converges to the agreement that machine learning methods emerged as some of the most prominent learning and classification approaches over the past decade. The CNN became one of most actively researched and broadly-applied deep machine learning methods. However, the training set has a large influence on the accuracy of a network and it is paramount to create an architecture that supports its maximum training and recognition performance. The problem considered in this article is how to prevent overfitting and underfitting. The deficiencies are addressed by comparing the statistics of CNN image recognition algorithms to the Ising model. Using a two-dimensional square-lattice array, the impact that the learning rate and regularization rate parameters have on the adaptability of CNNs for image classification are evaluated. The obtained results contribute to a better theoretical understanding of a CNN and provide concrete guidance on preventing model overfitting and underfitting when a CNN is applied for image recognition tasks.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.