Become a member
Sign in
Guibin Zhou
Guibin Zhou

Guibin Zhou

46 Following
11 Followers
  • Profile
  • Claps
  • Highlights

Highlighted by Guibin Zhou

See more

From Lasso and Ridge Regularization by Dk Kim

…t, both regularization does indeed prevent the model from overfitting, but I would like to think of Lasso Regularization as reducing the quantity of features while Ridge Regularization as reducing the quality of features. In essence, both types of reductions are needed, and therefore it makes much more sense why Elastic…

From BERT Technology introduced in 3-minutes by Suleiman Khan, Ph.D.

BERT’s state-of-the-art performance is based on two things. First, novel pre-training tasks called Masked Langauge Model(MLM) and Next Sentense Prediction (NSP). Second, a lot of data and compute power to train BERT.

Claps from Guibin Zhou

See more

HTTP/2: the difference between HTTP/1.1, benefits and how to use it

Factory.hr

TCP BBR : Magic dust for network performance.

Colt McAnlis

Speeding up BERT

Grigory Sapunov