| Home : December 02 2020 Computer News : Shrinking massive neural networks used to model language |
|
Shrinking massive neural networks used to model language |
December 02, 2020
Deep learning neural networks can be massive, demanding major computing power. In a test of the 'lottery ticket hypothesis,' researchers have found leaner, more efficient subnetworks hidden within BERT models. The discovery could make natural language processing more accessible.
Link: https://www.sciencedaily.com/releases/2020/12/201201144041.htm
|
|
|
|
|
