arXiv (Cornell University)· 2019· Preprint
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
- 1,008citations
- 2019year
Short summary
LogSparse Transformer incorporates causal convolutions for local context awareness and achieves O(L(log L)^2) memory complexity, outperforming state-of-the-art on time series forecasting.
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: Signal Processing
Signal ProcessingComputer Science