Models
Steps to learn and master a kind of model~
2W and 3H
What is the model for?
Like RNN Language Model is used for word prediction or words generation.
How is the model built?
Maybe some core structures or building blocks of the model, like filter-pooling layers in CNN.
How is the model trained?
The method this model is used for training and how to optimize its performance, backpropagation through time in RNN.
How to evaluate the model’s performance?
There are some evaluation metric for different kind of models, like perplexity for language models.
What are Pros and cons?
The advantages and disadvantages of this model.