Yekun's Note

Machine learning notes and writeup.

Fork me on GitHub

Pretraining on ImageNet followed by domain-specific fine-tuning has illustrated compelling improvements in computer vision research. Similarly, Natual Language Processing (NLP) tasks could borrow ideas from this.

Employing pretrained word representations or even langugage models to introduce linguistic prior knowledge has been common sense in amounts of NLP tasks with deep learning.

Pretrained word representation topology

Read more »

Active learning (called query learning or optimal experimental design in statistics). The key hypothesis is, if the learning algorithm is allowed to choose the data from what it learns, it will perform better with less training.

Read more »