PofoliaShared via Pofolia

arXiv (Cornell University)· 2014· Preprint

Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition

Vadim Lebedev, Yaroslav Ganin, Maksim Rakhuba, Ivan Oseledets et al.

Short summary

A two-step method decomposes convolutional kernels into smaller ones, achieving up to 8.5x CPU speedup on a character classification CNN with only a 1% accuracy drop.

AI-generated from the title and abstract; the full text is not read.

TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways, key points and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Field: Computational Mathematics

Computational MathematicsMathematics