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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep neural networks have achieved great success in many data processingapplications. However, the high computational complexity and storage cost makesdeep learning hard to be used on resource-constrained devices, and it is notenvironmental-friendly with much power cost. In this paper, we focus onlow-rank optimization for efficient deep learning techniques. In the spacedomain, deep neural networks are compressed by low rank approximation of thenetwork parameters, which directly reduces the storage requirement with asmaller number of network parameters. In the time domain, the networkparameters can be trained in a few subspaces, which enables efficient trainingfor fast convergence. The model compression in the spatial domain is summarizedinto three categories as pre-train, pre-set, and compression-aware methods,respectively. With a series of integrable techniques discussed, such as sparsepruning, quantization, and entropy coding, we can ensemble them in anintegration framework with lower computational complexity and storage. Besidesof summary of recent technical advances, we have two findings for motivatingfuture works: one is that the effective rank outperforms other sparse measuresfor network compression. The other is a spatial and temporal balance fortensorized neural networks.

Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training