:: Artikel Jurnal :: Kembali

Artikel Jurnal :: Kembali

Kinerja deep convolutional network untuk pengenalan aksara pallawa / Wiwien Widyastuti

Wiwien Widyastuti; (Media Teknika, 2017)

 Abstrak

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.

 Kata Kunci

 Metadata

No. Panggil : 620 MT 12:2 (2017)
Entri utama-Nama orang :
Subjek :
Penerbitan : Yogyakarta: Media Teknika, 2017
Sumber Pengatalogan : LibUI engind rda
ISSN : 14125641
Majalah/Jurnal : Media Teknika Jurnal Teknologi
Volume : Vol. 12, No. 2, Desember 2017: Hal. 115-123
Tipe Konten : text
Tipe Media : unmediated
Tipe Carrier : volume
Akses Elektronik :
Institusi Pemilik : Universitas Indonesia
Lokasi : Perpustakaan UI, Lantai 4, R. Koleksi Jurnal
  • Ketersediaan
  • Ulasan
No. Panggil No. Barkod Ketersediaan
620 MT 12:2 (2017) 03-18-472220852 TERSEDIA
Ulasan:
Tidak ada ulasan pada koleksi ini: 20471612