header
Image from OpenLibrary

Object recognition using deep convolutional neural networks / Amira Ahmad Alsharkawy Ibrahim ; Supervised Magda B. Fayek , Elsayed E. Hemayed , Samia A. Mashali

By: Contributor(s): Material type: TextTextLanguage: English Publication details: Cairo : Amira Ahmad Al Sharkawy Ibrahim , 2017Description: 112 P. : charts , facsimiles ; 30cmOther title:
  • التعرف على الأشياء بواسطة الشبكات العصبية التلفيفية العميقة [Added title page title]
Subject(s): Available additional physical forms:
  • Issued also as CD
Dissertation note: Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Computer Engineering Summary: We propose a system that integrates a convolutional neural network with bio-inspired features to exploit strengths of them, evaluate the performance of this integration and experimentations for providing better performance than the traditional convolutional neural networks. Our experiments trained on two datasets, CIFAR-10 and ImageNet, the largest dataset with high-resolution images. We run experiments over different GPUs, with different performances, like GT 740M and GTX 980. Furthermore, we provide a review study for the methods used for object recognition in the last decades until today and analysis study for some particular systems. The review study covers the traditional systems, the deep learning systems, and the cortical models, which are bio-inspired systems based on neuroscience experiments and researches to imitate the human visual systems
Tags from this library: No tags from this library for this title. Log in to add tags.
Star ratings
    Average rating: 0.0 (0 votes)
Holdings
Item type Current library Home library Call number Copy number Status Date due Barcode
Thesis Thesis قاعة الرسائل الجامعية - الدور الاول المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.06.M.Sc.2017.Am.O (Browse shelf(Opens below)) Not for loan 01010110074807000
CD - Rom CD - Rom مخـــزن الرســائل الجـــامعية - البدروم المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.06.M.Sc.2017.Am.O (Browse shelf(Opens below)) 74807.CD Not for loan 01020110074807000

Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Computer Engineering

We propose a system that integrates a convolutional neural network with bio-inspired features to exploit strengths of them, evaluate the performance of this integration and experimentations for providing better performance than the traditional convolutional neural networks. Our experiments trained on two datasets, CIFAR-10 and ImageNet, the largest dataset with high-resolution images. We run experiments over different GPUs, with different performances, like GT 740M and GTX 980. Furthermore, we provide a review study for the methods used for object recognition in the last decades until today and analysis study for some particular systems. The review study covers the traditional systems, the deep learning systems, and the cortical models, which are bio-inspired systems based on neuroscience experiments and researches to imitate the human visual systems

Issued also as CD

There are no comments on this title.

to post a comment.