English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep Neural Networks are known to be very demanding in terms of computing andmemory requirements. Due to the ever increasing use of embedded systems andmobile devices with a limited resource budget, designing low-complexity modelswithout sacrificing too much of their predictive performance gained greatimportance. In this work, we investigate and compare several well-known methodsto reduce the number of parameters in neural networks. We further put theseinto the context of a recent study on the effect of the Receptive Field (RF) ona model's performance, and empirically show that we can achieve high-performinglow-complexity models by applying specific restrictions on the RFs, incombination with parameter reduction methods. Additionally, we propose afilter-damping technique for regularizing the RF of models, without alteringtheir architecture and changing their parameter counts. We will show thatincorporating this technique improves the performance in various low-complexitysettings such as pruning and decomposed convolution. Using our proposed filterdamping, we achieved the 1st rank at the DCASE-2020 Challenge in the task ofLow-Complexity Acoustic Scene Classification.

Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping