Change search
ReferencesLink to record
Permanent link

Direct link
Convolutive Features for Storage and Transmission
KTH, School of Electrical Engineering (EES), Communication Networks. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre. (LCN)
2015 (English)Report (Other academic)
Abstract [en]

A central concern for many learning algorithms and sensing systems is how to efficiently store what the algorithm/system has learned. Convolutive Non-negative Matrix Factorization (CNMF) finds parts-based convolutive representations of non-negative data. Convolutive extensions of NMF have not considered storage efficiency as a side constraint during the learning procedure. We contribute an algorithm, Storable NMF (SNMF), that fuses ideas from the (1) parts-based learning and (2) integer sequence compression literature. SNMF enjoys the merits of both techniques: it retains the good-approximation properties of CNMF while also taking into account the size of the symbol set which is used to express the learned convolutive factors and activations. We demonstrate that SNMF yields a compression ratio ranging from 10:1 up to 20:1, which gives rise to a similar bandwidth and storage saving for networked sensors.

Trick: SNMF achieves these improved compression ratios, without incurring a significant loss of accuracy, by embedding an off-the-shelf compression algorithm in the CNMF updates so that quantization function updates are interleaved with CNMF’s up- date rules.

Place, publisher, year, edition, pages
Tübingen: Max Planck Institute for Intelligent Systems , 2015. , 1 p.
Keyword [en]
Machine Learning, Compression
National Category
Engineering and Technology
Research subject
Applied and Computational Mathematics
URN: urn:nbn:se:kth:diva-173394OAI: diva2:853025

QC 20150911

Available from: 2015-09-11 Created: 2015-09-11 Last updated: 2015-09-11Bibliographically approved

Open Access in DiVA

fulltext(2047 kB)25 downloads
File information
File name FULLTEXT01.pdfFile size 2047 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
de Fréin, Ruairí
By organisation
Communication NetworksACCESS Linnaeus Centre
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 25 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: 100 hits
ReferencesLink to record
Permanent link

Direct link