Cargando…
Discovering faster matrix multiplication algorithms with reinforcement learning
Improving the efficiency of algorithms for fundamental computations can have a widespread impact, as it can affect the overall speed of a large amount of computations. Matrix multiplication is one such primitive task, occurring in many systems—from neural networks to scientific computing routines. T...
Autores principales: | Fawzi, Alhussein, Balog, Matej, Huang, Aja, Hubert, Thomas, Romera-Paredes, Bernardino, Barekatain, Mohammadamin, Novikov, Alexander, R. Ruiz, Francisco J., Schrittwieser, Julian, Swirszcz, Grzegorz, Silver, David, Hassabis, Demis, Kohli, Pushmeet |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9534758/ https://www.ncbi.nlm.nih.gov/pubmed/36198780 http://dx.doi.org/10.1038/s41586-022-05172-4 |
Ejemplares similares
-
Faster sorting algorithms discovered using deep reinforcement learning
por: Mankowitz, Daniel J., et al.
Publicado: (2023) -
Advancing mathematics by guiding human intuition with AI
por: Davies, Alex, et al.
Publicado: (2021) -
Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13)
por: Senior, Andrew W., et al.
Publicado: (2019) -
Applying and improving AlphaFold at CASP14
por: Jumper, John, et al.
Publicado: (2021) -
Magnetic control of tokamak plasmas through deep reinforcement learning
por: Degrave, Jonas, et al.
Publicado: (2022)