Distilling knowledge from Neural Networks to build smaller and faster models
This article discusses GPT-2 and BERT models, as well using knowledge distillation to create highly accurate models with fewer parameters than their t…
Tag: neural networks
You sure? A Bayesian approach to obtaining uncertainty estimates from neural networks
In deep learning, there is no obvious way of obtaining uncertainty estimates. In 2016, Gal and Ghahramani proposed a method that is both theoretically…
