header

Variable length coding of quantized deep learning models / (Record no. 166860)

MARC details
000 -LEADER
fixed length control field 04264namaa22004211i 4500
003 - CONTROL NUMBER IDENTIFIER
control field OSt
005 - أخر تعامل مع التسجيلة
control field 20250223033238.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 240507s2023 |||a|||fr|m|| 000 0 eng d
040 ## - CATALOGING SOURCE
Original cataloguing agency EG-GICUC
Language of cataloging eng
Transcribing agency EG-GICUC
Modifying agency EG-GICUC
Description conventions rda
041 0# - LANGUAGE CODE
Language code of text/sound track or separate title eng
Language code of summary or abstract eng
Language code of sung or spoken text ara
049 ## - Acquisition Source
Acquisition Source Deposit
082 04 - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number 621.39
092 ## - LOCALLY ASSIGNED DEWEY CALL NUMBER (OCLC)
Classification number 621.39
Edition number 21
097 ## - Degree
Degree M.Sc
099 ## - LOCAL FREE-TEXT CALL NUMBER (OCLC)
Local Call Number Cai01 13 06 M.Sc 2023 Re.V
100 0# - MAIN ENTRY--PERSONAL NAME
Authority record control number or standard number Reem Omar Mohamed El-Sayed Abdel-Salam,
Preparation preparation.
245 10 - TITLE STATEMENT
Title Variable length coding of quantized deep learning models /
Statement of responsibility, etc. By Reem Omar Mohamed El-Sayed Abdel-Salam ; Under the Supervision of Prof. Dr. Amr G. Wassal, Dr. Ahmed H. Abdel-Gawad
246 15 - VARYING FORM OF TITLE
Title proper/short title طول متغير للترميز نماذج التعلم العميق الكمي /
264 #0 - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE
Date of production, publication, distribution, manufacture, or copyright notice 2023.
300 ## - PHYSICAL DESCRIPTION
Extent 67 pages :
Other physical details illustrations ;
Dimensions 30 cm. +
Accompanying material CD.
336 ## - CONTENT TYPE
Content type term text
Source rda content
337 ## - MEDIA TYPE
Media type term Unmediated
Source rdamedia
338 ## - CARRIER TYPE
Carrier type term volume
Source rdacarrier
502 ## - DISSERTATION NOTE
Dissertation note Thesis (M.Sc.) -Cairo University, 2023.
504 ## - BIBLIOGRAPHY, ETC. NOTE
Bibliography, etc. note Bibliography: pages 65-67.
520 ## - SUMMARY, ETC.
Summary, etc. Quantization plays a crucial role in efficiently deploying deep learning models on<br/>resource-constraint devices. Most of the existing quantization approaches require<br/>access either to the full dataset or a small amount of it, in order to re-train the<br/>model, which might be hard due to resources limitation for training or data access<br/>issues. Current methods achieve high performance on INT8 (or above) fixed-point<br/>integers. However, performance degrades with lower bit-width. Therefore, we<br/>propose variable length coding of quantized deep learning models (VLCQ), a<br/>data-free quantization method, which pushes the boundaries of quantization to<br/>have a higher accuracy performance with lower bit-width. VLCQ leverages from<br/>weight distribution of the model in quantization to improve accuracy, as well as to<br/>further compress weights, thus achieving lower bit-width. VLCQ achieves nearly<br/>the same FP32 accuracy with sub-6 bit-width for MobileNetV2 and ResNet18<br/>models. In addition to that, compared to the state of the art, VLCQ achieves<br/>similar accuracy while having 20% bit-width saving. Finally, for ResNet18 and<br/>Resnet50 models, VLCQ successfully quantizes them with 2 sub-bit-width with<br/>2-3% accuracy loss, making it the first data-free post-training quantization method<br/>to achieve good performance with very low bit-width.
520 ## - SUMMARY, ETC.
Summary, etc. يلعب التكميم دورًا مهمًا في نشر نماذج التعلم العميق بكفاءة على أجهزة قيود الموارد. معظم نهج التكميم الحالية تتطلب الوصول إلى مجموعة البيانات الكاملة أو كمية صغيرة منها بالترتيب لإعادة تدريب النموذج، والذي قد يكون صعبًا بسبب محدودية الموارد الخاصة به التدريب أو مشكلات الوصول إلى البيانات. الأساليب الحالية تحقق أداءً عاليًا في INT8 (أو أعلى) الأعداد الصحيحة ذات النقطة الثابتة. ومع ذلك، يتدهور الأداء مع عرض بت أقل. لذلك، نقترح ترميز متغير الطول للكمي نماذج التعلم العميق (VLCQ)، طريقة تكمية خالية من البيانات، تدفع حدود التكميم للحصول على أداء أعلى دقة مع عرض بت أقل. تستفيد VLCQ من توزيع الوزن للنموذج في التكميم لتحسين الدقة، وكذلك لزيادة ضغط الأوزان، وبالتالي تحقيق عرض بت أقل.
530 ## - ADDITIONAL PHYSICAL FORM AVAILABLE NOTE
Issues CD Issued also as CD
546 ## - LANGUAGE NOTE
Text Language Text in English and abstract in Arabic & English.
650 #7 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element Computer Engineering
Source of heading or term qrmark
653 #0 - INDEX TERM--UNCONTROLLED
Uncontrolled term Quantization
-- Post-training Quantization
-- Deep learning
-- Variable length encoding
-- deep neural networks
700 0# - ADDED ENTRY--PERSONAL NAME
Personal name Amr G. Wassal
Relator term thesis advisor.
700 0# - ADDED ENTRY--PERSONAL NAME
Personal name Ahmed H. Abdel-Gawad
Relator term thesis advisor.
900 ## - Thesis Information
Grant date 01-01-2023
Supervisory body Amr G. Wassal
-- Ahmed H. Abdel-Gawad
Discussion body Hoda Baraka
-- Ahmed F. Seddik
Universities Cairo University
Faculties Faculty of Engineering
Department Department of Computer Engineering
905 ## - Cataloger and Reviser Names
Cataloger Name Eman Ghareeb
Reviser Names Huda
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Koha item type Thesis
Edition 21
Suppress in OPAC No
Holdings
Source of classification or shelving scheme Home library Current library Date acquired Inventory number Full call number Barcode Date last seen Effective from Koha item type
Dewey Decimal Classification المكتبة المركزبة الجديدة - جامعة القاهرة قاعة الرسائل الجامعية - الدور الاول 07.05.2024 88286 Cai01 13 06 M.Sc 2023 Re.V 01010110088286000 07.05.2024 07.05.2024 Thesis