Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Compressing Deep Convolutional Neural Networks
KTH, School of Computer Science and Communication (CSC).
2017 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Deep Convolutional Neural Networks and "deep learning" in general stand at the cutting edge on a range of applications, from image based recognition and classification to natural language processing, speech and speaker recognition and reinforcement learning. Very deep models however are often large, complex and computationally expensive to train and evaluate. Deep learning models are thus seldom deployed natively in environments where computational resources are scarce or expensive. To address this problem we turn our attention towards a range of techniques that we collectively refer to as "model compression" where a lighter student model is trained to approximate the output produced by the model we wish to compress. To this end, the output from the original model is used to craft the training labels of the smaller student model. This work contains some experiments on CIFAR-10 and demonstrates how to use the aforementioned techniques to compress a people counting model whose precision, recall and F1-score are improved by as much as 14% against our baseline.

Place, publisher, year, edition, pages
2017. , 70 p.
Keyword [en]
machine learning neural networks image recognition
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:kth:diva-217316OAI: oai:DiVA.org:kth-217316DiVA: diva2:1155385
External cooperation
Axis Communications
Subject / course
Computer Science
Educational program
Master of Science - Machine Learning
Supervisors
Examiners
Available from: 2017-11-13 Created: 2017-11-07 Last updated: 2017-11-13Bibliographically approved

Open Access in DiVA

fulltext(2864 kB)4 downloads
File information
File name FULLTEXT01.pdfFile size 2864 kBChecksum SHA-512
50a28e7ebeffa5c4025a6765c0983725797f69f6e3968a74c0d1b9430681b2ef67dcd6b7ad764e084e3dbae39de4c56d83dd3f3f5bdf3f2549936ace98127350
Type fulltextMimetype application/pdf

By organisation
School of Computer Science and Communication (CSC)
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 4 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 18 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf