Kinerja Deep Convolutional Network untuk Pengenalan Aksara Pallawa
Abstract
This research trained Deep Convolutional Networks(ConvNets) to classify hand-written Pallava
alphabet. The Deep ConvNets architecture consists of two convolutional layers, each followed by maxpooling layer, two Fully-Connected layers. It had 442.602 parameters. This model classified 660 images
of hand-written Pallava alphabet into 33 diferent classes. To make training faster, this research used
GPU implementation with 384 CUDA cores. Two different techniques were implemented, Stochastic
Gradient Descent (SGD) and Adaptive Gradient, each trained with 10, 20, 30 and 40 epoch. The best
accuracy was 67,5%, achieved by the model with SGD technique trained at 30 epoch.
Keywords: Deep ConvNets, Pallava, GPU, SGD
Full Text:
PDFReferences
Aksara Pallawa. www.Wikipedia.org/ wiki/Aksara_Pallawa.
Yann L, Yoshua B, Geoffrey H. Deep Learning. Nature.2015; 521:436-444
Alex K, Ilya S, Geoffrey H. ImageNet Classification with Deep Convolutional Neural Network. Neural Information
Processing Systems Conference.2012
Pierre S, Soumith C, Yann L. Convolutional Neural Networks Applied to House Numbers Digit Classification.
International Conference on Pattern Recognition (ICPR 2012). 2012.
Michael A.N., Neural Networks and Deep Learning. Determination Press.2015.
Wiwien W. Pengenalan Aksara Pallawa Dengan Model Hidden Markov. RETII XI. Yogyakarta. 2016;XI:6.
Adeshpande. A Beginners Guide To Understanding Convolutional Neural-Networks. 2017
Adrian R, Lenet Convolutional Neural Network in Python. Deep Learning Tutorials. 2016.
Yan L, Bottou, Bengio, Haffner. Gradient-based Learning Applied to Document Recognition. Proc. IEEE. 1998;
(11): 22782324.
DOI: https://doi.org/10.24071/mt.v12i2.1085
Article Metrics
Abstract view : 1780 timesPDF view: 1460 times
Refbacks
- There are currently no refbacks.