How Long Does It Take To Learn Geometry

How to learn Deep Learning in 6 months

It is quite possible to learn, follow and contribute to land-of-fine art work in deep learning in nigh 6 months' time. This commodity details out the steps to achieve that.

Pre-requisites

- You are willing to spend 10–20 hours per week for the next 6 months
- You lot have some programming skills. You lot should be comfy to choice up Python along the way. And cloud. (No background in Python and cloud assumed).
- Some math instruction in the past (algebra, geometry etc).
- Access to internet and figurer.

Step 1

We learn driving a machine — by driving. Non by learning how the clutch and the internal combustion engine work. Atleast not initially. When learning deep learning, we will follow the same elevation-down approach.

Do the fast.ai class — Practical Deep Learning for Coders — Role i. This takes near 4–vi weeks of endeavor. This course has a session on running the lawmaking on deject. Google Colaboratory has free GPU access. Start with that. Other options include Paperspace, AWS, GCP, Crestle and Floydhub. All of these are corking. Exercise non start to build your ain automobile. Atleast non yet.

Step 2

This is the fourth dimension to know some of the basics. Learn most calculus and linear algebra.

For calculus, Big Motion-picture show of Calculus provides a good overview.

For Linear Algebra, Gilbert Strang's MIT course on OpenCourseWare is astonishing.

Once you finish the above two, read the Matrix Calculus for Deep Learning.

Step 3

Now is the time to empathize the bottom-up arroyo to deep learning. Do all the 5 courses in the deep learning specialisation in Coursera. Y'all need to pay to become the assignments graded. Just the effort is truly worth information technology. Ideally, given the background you have gained then far, you should exist able to complete i class every week.

Pace 4

"All piece of 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 trouble of your liking.

The first iii steps are about understanding how and where to utilize 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.

Pace five

At present go and practise fast.ai's function II course — Cutting Edge Deep Learning for Coders. This covers more avant-garde topics and you will learn to read the latest research papers and brand sense out of them.

Each of the steps should accept about 4–6 weeks' fourth dimension. And in about 26 weeks since the time you started, and if you followed all of the above religiously, yous will have a solid foundation in deep learning.

Where to go next?

Practice the Stanford's CS231n and CS224d courses. These ii are amazing courses with great depth for vision and NLP respectively. They embrace the latest land-of-art. And read the deep learning volume. This will solidify your understanding.

Happy deep learning. Create every unmarried day.