It is quite possible to learn machine learning subjects in less than 6 month’s time and this article would guide you through the resources available to get there.
Pre-requisites
– 10-20 hours per month for next 6 months
– Basic programming skills since most machine learning uses Python
– Good with Maths (Algebra, Geometry…etc)
The best way to learn machine learning is to get your hands dirty.
1. Start Small
Do the fast.ai course — Practical Deep Learning for Coders — Part 1. This takes about 4–6 weeks of effort. This course has a session on running the code on cloud. Google Colaboratory has free GPU access. Start with that. Other options include Paperspace, AWS, GCP, Crestle, and Floydhub. All of these are great. Do not start to build your own machine. At least not yet.
2. Get into Maths
This is the time to know some of the basics. Learn about calculus and linear algebra. For calculus, Big Picture of Calculus provides a good overview. For Linear Algebra, Gilbert Strang’s MIT course on OpenCourseWare is amazing. Once you finish the above two, read the Matrix Calculus for Deep Learning.
3. Time for some assessments
Now is the time to understand the bottom-up approach to deep learning. Do all the 5 courses in the deep learning specialisation in Coursera. You need to pay to get the assignments graded. But the effort is truly worth it. Ideally, given the background you have gained so far, you should be able to complete one course every week.
4. Capstone Project
“All work and no play makes Jack a dull boy”
Do a capstone project. This is the time where you delve deep into a deep learning library(eg: Tensorflow, PyTorch, MXNet) and implement an architecture from scratch for a problem of your liking. The first three steps are about understanding how and where to use deep learning and gaining a solid foundation. This step is all about implementing a project from scratch and developing a strong foundation on the tools.
5. Advanced Machine Learning
Now go and do fast.ai’s part II course — Cutting Edge Deep Learning for Coders. This covers more advanced topics and you will learn to read the latest research papers and make sense out of them. Each of the steps should take about 4–6 weeks’ time. And in about 26 weeks since the time you started, and if you followed all of the above religiously, you will have a solid foundation in deep learning.
What’s next?
Do the Stanford’s CS231n and CS224d courses. These two are amazing courses with great depth for vision and NLP respectively. They cover the latest state-of-art. And read the deep learning book. This will solidify your understanding.
Happy deep learning. Create every single day.
Credit: Bargava @ Towardsdatascience
