header
Image from OpenLibrary

Algorithms to enhance the accuracy and adaptability of deep learning models with applications in machine learning / Ahmad Abdelmoneim Alsallab ; Supervised Mohsen A. Rashwan

By: Contributor(s): Material type: TextTextLanguage: English Publication details: Cairo : Ahmad Abdelmoneim Alsallab , 2014Description: 127 P. : plans , facsimiles ; 30cmOther title:
  • خواريزمات لتحسين دقة التمييز و قدرة التكيف لنماذج التعلم العميقة و تطبيقاتها فى مجال التعلم الألى [Added title page title]
Subject(s): Available additional physical forms:
  • Issued also as CD
Dissertation note: Thesis (Ph.D.) - Cairo University - Faculty of Engineering - Department of Electronics and Communication Summary: In this thesis three new algorithms are introduced to enhance the accuracy of classification and adaptation of deep learning models. The first contribution is the Self-learning machines (SLM) model. The second contribution is the new Basic Unit Reuse architecture. The third contribution is the confused sub-set resolution algorithm. Evaluation of the proposed algorithms is made on datasets like TIMIT, MNIST, Reuters, 20Newsgroups, LDC ATB{u2026}etc. Experimental results show that the proposed algorithms outperform the published baselines. Improvements range from 0.7% to 2% representing 10% to 15% overall error improvement
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 Cai01.13.08.Ph.D.2014.Ah.A (Browse shelf(Opens below)) Not for loan 01010110063479000
CD - Rom CD - Rom مخـــزن الرســائل الجـــامعية - البدروم المكتبة المركزبة الجديدة - جامعة القاهرة Cai01.13.08.Ph.D.2014.Ah.A (Browse shelf(Opens below)) 63479.CD Not for loan 01020110063479000

Thesis (Ph.D.) - Cairo University - Faculty of Engineering - Department of Electronics and Communication

In this thesis three new algorithms are introduced to enhance the accuracy of classification and adaptation of deep learning models. The first contribution is the Self-learning machines (SLM) model. The second contribution is the new Basic Unit Reuse architecture. The third contribution is the confused sub-set resolution algorithm. Evaluation of the proposed algorithms is made on datasets like TIMIT, MNIST, Reuters, 20Newsgroups, LDC ATB{u2026}etc. Experimental results show that the proposed algorithms outperform the published baselines. Improvements range from 0.7% to 2% representing 10% to 15% overall error improvement

Issued also as CD

There are no comments on this title.

to post a comment.