arXiv (Cornell University)· 2014· Preprint
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
- 331citations
- 2014year
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 openField: Computational Mathematics
Computational MathematicsMathematics