Please use this identifier to cite or link to this item:
Title: Fast convolutional neural network for image classification
Authors: Jeon, Young Seok
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
DRNTU::Science::Mathematics::Applied mathematics::Optimization
Issue Date: 2017
Abstract: Convolutional Neural Network(CNN) has proven its excellence in various classification tasks over the recent years. However, the major drawback of deep CNN was its days of computation time to train on large dataset with thousands of classes. The main cause for this slow computation is mostly due to the convolutional layers which performs 2D convolutions with lots of for-loops. This paper thus seeks for faster convolution algorithms such as FFT, Winograd and im2col convolutions to minimize the overall computation time and also introduces CNN written in Matlab for image classification tasks. Performance of the fast CNN algorithm written in Matlab is tested on MNIST and CIFAR-10 dataset with CNN architecture with [3*3] filter Convolutional layer sets(Convolutional, pooling and Sigmoid layers) , Fully Connected(FC) layer and followed by a Softmax layer.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
1.82 MBAdobe PDFView/Open

Page view(s) 50

Updated on May 9, 2021

Download(s) 50

Updated on May 9, 2021

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.