Appropriate Number of Standard 2 × 2 Max Pooling Layers and Their Allocation in Convolutional Neural Networks for Diverse and Heterogeneous Datasets

Romanuke Vadim V. ()
Additional contact information
Romanuke Vadim V.: Polish Naval Academy, 69 Śmidowicza Street, Gdynia, Poland

Information Technology and Management Science, 2017, vol. 20, issue 1, 12-19

Abstract: A problem of appropriately allocating pooling layers in convolutional neural networks is considered. The consideration is based on CIFAR-10, NORB, and EEACL26 datasets for preventing “overfitting” in a solution of the problem. For highly accurate image recognition within these datasets, the networks are used with the max pooling operation. The most common form of such operation, which is a 2 × 2 pooling layer, is applied with a stride of 2 without padding after convolutional layers. Based on performance against a series of the network architectures, a rule for the best allocation of max pooling layers is formulated. The rule is to insert a few pooling layers after the starting convolutional layers and to insert a one pooling layer after the last but one convolutional layer (“11...100...010”). For much simpler datasets, the best allocation is “11...100...0”.

Keywords: Convolutional neural network; max pooling layer (search for similar items in EconPapers)
Date: 2017
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1515/itms-2017-0002 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:vrs:itmasc:v:20:y:2017:i:1:p:12-19:n:2

DOI: 10.1515/itms-2017-0002

Access Statistics for this article

Information Technology and Management Science is currently edited by J. Merkurjevs

More articles in Information Technology and Management Science from Sciendo
Bibliographic data for series maintained by Peter Golla ().