Optimization of Convolutional Neural Networks for Constrained Devices through Binarization
Public Deposited- Resource Type
- Creator
- Contributors
- copyright copyright (Copyright list)
- Abstract
CNNs are the most common branch of Deep Neural Networks (DNNs), and they are structures with a strong capability for feature extraction. By using CNNs, a nonlinear model is trained to map an input space to a corresponding output space. These high-performance CNNs come with a high computational cost and the need for huge memory storage due to the chains of many Convolutional Layers (usually more than 50 layers). To address these issues, a variety of algorithms have been proposed in recent years. In this research, we present a solution that is a combination of several different approaches. and based on matrix optimization, parameters binary quantization, and data parallelism programming techniques. We show that our method significantly outperforms the current conventional PyTorch convolution operation with less memory usage and better computational budget when tested in different scenarios.
- Subject
- Language
- Publisher
- Thesis Degree Level
- Thesis Degree Name
- Thesis Degree Discipline
- Identifier
- Rights Notes
Copyright © 2022 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Date Created
- 2022
Relations
- In Collection:
Items
Thumbnail | Title | Date Uploaded | Visibility | Actions |
---|---|---|---|---|
rouhandeh-optimizationofconvolutionalneuralnetworks.pdf | 2023-05-05 | Public | Download |