OPTIMASI PENGENALAN KARAKTER ARAB TULISAN TANGAN MENGGUNAKAN MODEL HYBRID QUANTUM CONVOLUTIONAL NEURAL NETWORK (QCNN) DENGAN TEKNIK DENSE ANGLE ENCODING

Haerul Anam, NIM.: 24206051019 (2026) OPTIMASI PENGENALAN KARAKTER ARAB TULISAN TANGAN MENGGUNAKAN MODEL HYBRID QUANTUM CONVOLUTIONAL NEURAL NETWORK (QCNN) DENGAN TEKNIK DENSE ANGLE ENCODING. Masters thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (OPTIMASI PENGENALAN KARAKTER ARAB TULISAN TANGAN MENGGUNAKAN MODEL HYBRID QUANTUM CONVOLUTIONAL NEURAL NETWORK (QCNN) DENGAN TEKNIK DENSE ANGLE ENCODING) 24206051019_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (7MB) | Preview
	Text (OPTIMASI PENGENALAN KARAKTER ARAB TULISAN TANGAN MENGGUNAKAN MODEL HYBRID QUANTUM CONVOLUTIONAL NEURAL NETWORK (QCNN) DENGAN TEKNIK DENSE ANGLE ENCODING) 24206051019_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (13MB) | Request a copy

Abstract

Handwritten Arabic character recognition faces challenges due to variations in writing styles and morphological similarities, particularly among homoglyph characters that differ in the number or position of dots. In a Hybrid Quantum Convolutional Neural Network (HQCNN), these challenges are also related to limitations in feature representation when latent CNN features are mapped to a quantum circuit. Standard Angle Encoding maps one feature to one qubit, causing the required number of qubits to increase with the feature dimension. This study aims to develop and evaluate a Hybrid Quantum Convolutional Neural Network (HQCNN) with Dense Angle Encoding (DAE) for handwritten Arabic character recognition and to analyze the effect of

Share this knowledge with your friends :

Actions (login required)

View Item