Hybrid ResNet: A Shallow Deep Learning Architecture for Moderate Datasets

Ghulam Murtaza, Obaid-Ur-Rehman, Muhammad K. Shahzad, S. M. Riazul Islam, Mahmud Hossain, Kyung Sup Kwak

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Deep learning models usually require large memory space and computation power for training on vast size datasets. This costly overhead creates a bottleneck in the research and development of neural network models. Efficient and resourceful deep learning models that work on the balance between computation cost and performance are required. Given these scenarios of less performance improvement over exponential computational cost increase, we have implemented two shallow neural network architectures based on ResNet. One is the naive version of the ResNet model; keeping its main design features and configuration. The second model uses a combination of residual and non-residual blocks primarily for effective feature learning and computation efficiency. We compare and evaluate these architectures performance in a rather simple environment. We found that simple Resnet in less number of layers is computationally expensive for small datasets. Performance improvement is observed with our custom architecture of ResNet. This new approach can be implemented for larger-scale neural networks for achieving computation efficiency.

Original languageEnglish
Title of host publicationICTC 2021 - 12th International Conference on ICT Convergence
Subtitle of host publication"Beyond the Pandemic Era with ICT Convergence Innovation"
PublisherIEEE Computer Society
Pages1679-1682
Number of pages4
ISBN (Electronic)9781665423830
ISBN (Print)9781665423847
DOIs
Publication statusPublished - 7 Dec 2021
Externally publishedYes
Event12th International Conference on Information and Communication Technology Convergence - Jeju Island, Korea, Republic of
Duration: 20 Oct 202122 Oct 2021
Conference number: 12

Publication series

NameInternational Conference on ICT Convergence
PublisherIEEE
Volume2021-October
ISSN (Print)2162-1233
ISSN (Electronic)2162-1241

Conference

Conference12th International Conference on Information and Communication Technology Convergence
Abbreviated titleICTC 2021
Country/TerritoryKorea, Republic of
CityJeju Island
Period20/10/2122/10/21

Cite this