Machine Learning and Data Science Resources

A collection of data science related resources that helped me with my journey so far

I transitioned into the field of data science from software development about 1.5 years ago. In this post, I aim to share a list of resources that I personally found helpful in my journey so far. If you’re someone who is just getting started, preparing for interviews, or looking for new material, I hope you find this useful. I’ve divided these resources into groups.

Interview Preparation

There’s a wide variety of roles available in this field — Data Scientist, Product Analyst, Data Analyst, Data Engineer, Machine Learning Engineer, Computer Vision Engineer etc., and each role has specific focus areas. However, here’s a general list of topics that I found to be covered to some extent in each role:

Machine learning and Deep Learning Fundamentals

1. I found this great repo covering most topics related to Machine learning and Deep learning that might be relevant for interviews.

2. This is a comprehensive overview of different gradient descent algorithms and their evolution over the years. You can also check out more blogs from the author here: https://ruder.io/

Programming

1. Leetcode is a great platform for coding practice and has curated lists of programming questions for a wide variety of topics. However, it can be quite overwhelming to go through each of them, so here’s a list of Leetcode questions I found covering most common patterns:

2. If you’re looking to really understand algorithm fundamentals and complexity analysis, I highly recommend reading this book I was introduced to in the first programming course I ever took in my undergrad. I’ve gone through the main sections (Sorting, Searching, Dynamic programming, Complexity Analysis, and Graph-based algorithms) multiple times.

3. My brother has been a huge source of motivation and guidance to me. He also happens to be a data science educator and provides a mentorship program, check out his courses to learn more:

If you’re looking for guided interview preparation with one-on-one attention for the Data Analyst role, you could check out this Bootcamp:

SQL

Pandas

A/B Testing

Data Science Communities

Data Science communities are a really effective way to get in touch with like-minded people, learn about current trends and events in the field, and meet and get advice /mentorship from industry experts. Here are a few communities I’m a part of :

1. Jovian Pro provides a Slack community where you can get one-on-one guidance from industry experts, project recommendations, resume review, and find people to work with on group projects/ hackathons.

2. Workera is a great platform that provides assessments to measure your data science skills and improve on them, it also gives you job recommendations based on your skill level. They have a Slack community as well.

3. I’m sure you’ve heard of Kaggle, it hosts a lot of data science competitions and has an amazing collection of datasets. Participating in these competitions can be a really good learning experience.

Study Materials

Fundamentals — Statistics, Linear Algebra, Programming and Database Management

Whether you aim to be a computer vision scientist or a Data Analyst, you would need to have a strong understanding of these fundamental topics.

Statistics

Linear Algebra

I highly recommend going through this series called the Essence of Linear Algebra, which helped me get an intuitive understanding of basic concepts through amazing visuals and animations.

Programming

Most data science jobs expect an intermediate-level proficiency in Python. Here’s a resource that helped me get started:

Apart from this, I’ve already mentioned a few more resources in the Interview preparation section above.

Database Management Systems

I learned DBMS through my courses in undergrad but here is an online resource I found helpful:

Machine Learning

Andrew Ng’s Machine Learning course is probably the most popular one and for good reason, it helped me grasp a solid understanding of ML fundamentals.

Deep Learning

1. The deeplearning.ai specialization on Coursera is a great follow-up to the Machine learning course mentioned above.

2. Another course I found very helpful is fast.ai offered by Jeremy Howard. This course in fact inspired me to pursue a Master’s in Data Science at the University of San Francisco

3. PyTorch

Pytorch is a really popular machine learning framework and I’ve written several beginner-friendly blogs on it. I recommend checking out this course if you want a deeper understanding:

4. Tensorflow

Tensorflow is the other most popular deep learning framework. It was developed by Google and is used in a lot of production-level machine learning applications, it also integrates very smoothly with the entire Google Cloud infrastructure. Here’s a good course that helped me get started with Tensorflow on Google cloud:

Natural Language Processing

Here’s a blog I recently wrote for anyone who is just getting started with NLP

Once you’re familiar with the basics, this course from Stanford is a comprehensive one:

Computer Vision

I highly recommend this popular course on Computer Vision offered by Stanford

Conclusion

Data Science is a rapidly growing field and it is important to always keep learning, I hope to keep adding to this list as I come across more useful resources.