Charting My Path: A Roadmap for the Next Few Months

Ever since I decided that I want to be a machine learning engineer, I have never stopped feeling overwhelmed by the topics I need to learn and the concepts I need to cover. It's absolutely staggering, both in depth and breadth. The resources are plentiful—so many choices, so many options, so many books, articles, and more. It's very difficult to choose what is best for you. Every time I sit down to learn, I am bombarded with these resources. This has made me pause and give up many times. When I start reading about a topic, I often come across related concepts or ideas that catch my attention, causing me to shift focus. This constant switching makes it difficult to retain progress, leaving me feeling as though I'm not learning effectively. This happens a lot. Hence, I thought I would block out all the unnecessary noise and just focus on what I want to learn—what I need to learn. I decided to choose a book, a course, or a video, commit to it, and focus only on that before moving on to the next. What you're looking at is my carefully curated collection of resources that I have decided to conquer in the next few months.

Traditional ML

• Introduction to Statistical Learning (ISLR): have read the first 2 chapters, needs to complete the rest
• ML Engineering - Andy Burkov: completed this book about 2 years back, need to revisit.

Deep Learning

• Dive into Deep Learning
• Deep Learning with Python - Francois Chollet
• Deep Learning at Scale

LLMs (Large Language Models)

• Hands-on Large Language Models: In Progress
• Build a LLM from Scratch

ML System Design

• Designing ML Systems - Chip Huyen: this is done and highly recommended
• Reliable Machine Learning: In Progress
• ML Design Patterns
• Architecting Data and Machine Learning Platforms

System Design

• DDIA - Designing Data Intensive Applications
• CPU Land
• Onsites FYI

DSA

• Neetcode 150