How would I learn machine learning today?
One of the most frequent questions I get is “How would you learn machine learning if you were starting today?”. I thought that it might be…
One of the most frequent questions I get is “How would you learn machine learning if you were starting today?”. I thought that it might be worth it to actually write it out and share it with all of you. Here’re 5 things I’d do if I were starting over today…
Tip #1: Get Going
Tip #2: Build your Fundamentals
Don’t worry about which framework to learn. Pick whichever one you like and run with it. What’s really important is that you learn the fundamentals. Pytorch, Tensorflow, and Jax are all frameworks that help you solve problems, but the fundamentals that they implement are the same. Focus on those first. Every time.
Frameworks come and go, fundamentals come and grow.
Tip #3: Read and Implement Papers
Forget trying to keep up with all the advances in the field. Machine learning moves way too fast. Instead, understand the implementations of papers you’re reading and reimplement them yourself. That will help you tremendously and compound your learning.
The best papers of today will become the textbooks of tomorrow.
Tip #4: Learn Publicly
Write about what you learn and share it publicly. You don’t need to be an expert. There are a million others who have the same questions you do. Make their lives easier. Share your knowledge. This is the step that everyone skips. Learning in public will build connections that you previously may have missed.
Tip #5: Be a T-shaped learner
Dive Deep into your area of interest like Computer Vision but explore other areas like Natural Language Processing, Recommenders, and Graph learning.
Great research ideas are the byproduct of cross pollination.
If you’re not sure where to start, Begin your Kaggle journey seriously. Competing with the best in the world will raise your level and will accelerate your learning.
🤖💪 Want more ideas to be a productive ML practitioner?
Each week, I send out a newsletter with practical tips and resources to level up as a machine learning practitioner. Join here for free →