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

Information Technology and Management Science 2017
Vadim V. Romanuke

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”.

Atslēgas vārdi
Convolutional neural network, max pooling layer

Romanuke, V. Appropriate Number of Standard 2 × 2 Max Pooling Layers and Their Allocation in Convolutional Neural Networks for Diverse and Heterogeneous Datasets. Information Technology and Management Science, 2017, Vol. 20, 12.-19. lpp. ISSN 2255-9086. e-ISSN 2255-9094.

Publikācijas valoda
English (en)