Effects of Hyper-parameters and Dataset on CNN Training
- Authors
- 응웬휘난; 이찬호
- Issue Date
- Mar-2018
- Publisher
- 한국전기전자학회
- Keywords
- Hyper-parameter; CNN; classification accuracy; weight factor; neural network training
- Citation
- 전기전자학회논문지, v.22, no.1, pp.14 - 20
- Journal Title
- 전기전자학회논문지
- Volume
- 22
- Number
- 1
- Start Page
- 14
- End Page
- 20
- URI
- http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/31863
- ISSN
- 1226-7244
- Abstract
- The purpose of training a convolutional neural network (CNN) is to obtain weight factors that give high classification accuracies. The initial values of hyper-parameters affect the training results, and it is important to train a CNN with a suitable hyper-parameter set of a learning rate, a batch size, the initialization of weight factors, and an optimizer. We investigate the effects of a single hyper-parameter while others are fixed in order to obtain a hyper-parameter set that gives higher classification accuracies and requires shorter training time using a proposed VGG-like CNN for training since the VGG is widely used. The CNN is trained for four datasets of CIFAR10, CIFAR100, GTSRB and DSDL-DB. The effects of the normalization and the data transformation for datasets are also investigated, and a training scheme using merged datasets is proposed.
- Files in This Item
-
Go to Link
- Appears in
Collections - College of Information Technology > ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/31863)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.