So far, we’ve covered most of the things that we should know about machine learning, including concepts, optimization, and popular models under the hood. Yet, some advanced techniques, such as the Gaussian Process and MCMC, are not mentioned. We will talk about them later. From now on, we will move to Deep Learning. But before that, we are going to revisit some math knowledge.

The most popular deep learning frameworks nowadays are Tensorflow and PyTorch. Well, during my study, I use PyTorch more often. Recently, I am building the classic BiLSTM-CRF model using PyTorch. It’s a bit hard for me when operating matrices since it uses various advanced techniques about indexing and slicing. I think it’s necessary to explain these amazing functions. Therefore, I am going to write this post to revisit the most important aspects of PyTorch for future references.

Data structure and algorithms are two important courses in Computer Science. Knowing how to utilise appropriate data structures and algorithms to fit our problems can greatly decrease memory space and improve performance. Besides, the ideas behind the classical algorithms are also worth learning to strengthen our logical thinking skills. Well, this series of articles are simply quick notes to help refresh my knowledge for future reference. So let’s start from sorting.

In the last post, we talked about text preprocessing techniques. However, even the data is clean now, they are still text. We still haven’t answered the question: how to covert text into numbers? In NLP parlance, this is called text representation.

From now on, we will focus on a specific domain — Natural Language Processing(NLP), in part because my summer project is about Named Entities Recognition(NER). Therefore, I need to know some text preprocessing techniques and have a good understanding of the state-of-art NLP models, particularly BiLSTM + CRF. The very first step in NLP is text preprocessing, so I am going to start from here.