I recently graduated with a BS in computer science and have started a backend Java engineering job. However, my primary interest lies in machine learning (ML) and data science (DS), and I aim to transition into an ML engineering role in the future. During college, I took courses in DS, ML, and natural language processing (NLP), and I’ve worked on various algorithms, trained models, and completed several data science projects. However, I feel I haven’t delved deep enough into understanding the underlying mathematics and algorithms.
Could anyone recommend books that delve into the depths of this field? My main focus is on NLP, and I’d prefer shorter, less textbook-like reads, as I struggle with that format. If anyone has come across books like “Clean Code” or “Clean Architecture” by Robert C. Martin, which are structured like textbooks but are more accessible, I’d appreciate similar suggestions in the DS and ML domain.
I’m eager to hear your recommendations!
1 Like
Natural Language Processing in Python by Steven Bird, Ewan Klein, and Edward Loper - This book offers practical insights into NLP techniques using Python, providing hands-on experience with real-world applications.
Congrats on the CS grad and the backend job, that’s awesome! Totally understand the pull of machine learning (ML) and data science (DS) though, it’s fascinating stuff. I went through a similar thing, wanting to switch from coding to ML after college.
Here’s the good news: Your experience with DS, ML, and NLP courses is a great foundation! The projects and model training you did are super valuable. To really solidify those concepts, though, you’re right about needing a deeper dive into the math and algorithms.
The key is finding resources that aren’t super textbook-y. I hear you on that! For ML and DS in general, check out “Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow” by Aurélien Géron. It’s practical and explains things clearly, with code examples. Think of it as a really good teacher, not a dusty textbook.
For NLP specifically, “Speech and Language Processing” by Dan Jurafsky and James H. Martin is a great choice. It goes a bit deeper but is still really approachable. Imagine it like a college lecture from an expert who makes it interesting, not overwhelming.
I suggest Simon Prince’s “Understanding Deep Learning” if you’re interested in deep learning. The book is well worth the extra money, even though it is on the expensive side. You don’t need to know a lot of background material to understand the principles that are taught in the book because it is self-explanatory and provides current information. It has a ton of illustrations and instructions, so you won’t have to worry about information that is out of current. Best of luck Lucy.
