# Start Your Machine Learning Career in Quarantine

While this quarantine can last two months, make the most of it by starting your career in Machine Learning with this 60-day learning plan.

*Photo by Alex Knight on Unsplash.*

In this article, I outline a full curriculum for machine learning, considering this quarantine will stick around for at least 2 months.

### Python (Day 0 — Day 10)

*Photo by Hitesh Choudhary on Unsplash.*

Start with Python. It is the most used language in Machine Learning/Data Science. You can learn the basics of it easily in 3 days. Follow along with this Youtube series by Sentdex. You will learn all the functional programming in Python.

Now learn Object-Oriented Programming, List Comprehensions, and Lambda Functions in Python so that you can easily start in Machine Learning.

Now I assume that you know the basics of programming Python, so you can read, write, and understand code in Python.

### Important Libraries (Day 10 — Day 15)

*Photo by Clay Banks on Unsplash.*

3 of the most important libraries for a Data Scientist/ Machine Learning Engineer are

- Numpy
- Pandas
- Matplotlib

Now, I don't recommend learning from a single place, so these 2 tutorials will be enough to get starting knowledge of Numpy, Pandas, and Matplotlib.

Now, I believe you can complete these 2 tutorials in 2 days, so for the next 3 days, download a dataset from Kaggle, apply all the things you learned on that dataset. It is okay to fail on that dataset, but you’ll have a better idea.

### Math (Day 15 — Day 22)

*Photo by Antoine Dautry on Unsplash.*

Now, this is an important part. I want you to have at least a good grip on linear algebra and calculus and probability theory. Give 2 days to Linear algebra, 2 days to Calculus, 3 days to Probability theory to learn the basics of all these.

- Linear Algebra for Beginners — Linear Algebra for Machine Learning
- Mathematics for Machine Learning Full Course: Calculus || Part 2 || Calculus for Machine Learning
- Statistics for Data Science

### Basics of Machine Learning Algorithms (Day 22 — Day 30)

*Photo by Clarisse Croset on Unsplash.*

In these 8 days, you have to learn the basics of Machine Learning Algorithms, some math, and the intuition behind them. Now there is no better course then Andrew NG Machine Learning course by Stanford University at Coursera.

You do not have to attempt the full course, just watch the videos and take some notes, skip Matlab & Mathematics part, and skip all programming assignments. Just watch videos and learn some basics in these 13 days to understand how machine learning works behind the scenes.

I know this course is lengthy, and it is hard to do in 8 days, but if you give 3–4 hours per day, you can easily complete it in 8 days.

### Apply these algorithms (Day 30 — Day 40)

*Photo by Tommy Lisbin on Unsplash.*

This free course by Udacity taught by Sebastian Thrun, one of the big names in the industry, founder and president of Udacity, is very good to apply machine learning algorithms. You will learn some new algorithms, such as Naive Bayes and Decision Trees. You will learn how to use Sci-kit Learn, a Python framework for applying machine learning algorithms, which will make your life a lot easier.

### Foundations of Deep Learning (Day 40 — Day 45)

Complete course 1 of the Deep Learning Specialization by deeplearning.ai at Coursera. You will learn all the basic fundamentals of Neural Networks and able to create one using Numpy. You will learn fundamental concepts such as Forward Propagation and Back Propagation.

### TensorFlow in Practice (Day 45 — Day 60)

*Photo by Mitchell Luo on Unsplash.*

Tensorflow is a Deep learning framework by Google, having a high reputation, and job value in the market.

Complete this Tensorflow Specialization by deeplearning.ai at coursera to learn about TensorFlow, a modern deep learning framework, in-depth. Average time to complete this specialization is 1 month with 16 hours a week, but if you give 4 hours daily, you can easily complete it in fifteen days. You will get a good grip on practical Computer Vision Problems, Natural Language Processing Problems, and Time-series and Sequence problems. In short, you will learn a lot.

In case you have completed these courses before Day 60, these are some other suggestions for you to follow.

- Fast.ai for a very practical course
- Deep Learning Book
- CS231n for in-depth Convolutional Neural Networks to get better at Computer Vision
- CS224n Natural Language Processing

Now you know a lot about machine learning and deep learning, try making connections with people and try to land an internship, also go to kaggle.com and practice on their data sets to become better.

**Related:**