Thanks to Hamza Khalid for contributing this article!

Numerous learners strive to discover the right starting point when they step into the field of Artificial Intelligence (AI). This article intends to accumulate some of the comprehensive learning resources for students who aspire to pursue Machine learning (ML), Deep learning (DL), or Computer Vision (CV) careers.


  1. Machine Learning (ML) is a subset of AI. Arthur Samuel wrote about ML in 1959, “(It is a) field of study that gives computers the ability to learn without being explicitly programmed.”
    Applications: Spam filtering, Facebook Ads, Amazon and Netflix recommender system, etc
  2. Deep Learning (DL) is a subset of Machine Learning where artificial neural networks mimic the human brain and learn from a large amount of data.
    Applications: Speech Recognition, Natural Language Processing, Social Network filtering, etc.
  3. Computer Vision (CV) allows computers to see and perceive their surroundings in the same way humans do.
    Applications: Self-driving cars, facial recognition systems, Amazon Go, etc.

Step 1 | Learn to Program

Before plunging into AI, you must have a solid grasp of Python or R programming language. Here are some valuable links to master Python:

  1. EdX Introduction to Computer Science and Programming (FREE, Add a Verified Certificate for USD 75)
  2. Google for Education Python (FREE, No certificate)
  3. EdX Introduction to Python Introduction to Python (FREE, Add a Verified Certificate for USD 99)
  4. Coursera Python for Everybody Specialization (FREE without a certificate but Financial Aid is available)
  5. w3schools Python (FREE, Add a verified certificate for USD 95)

Step 2 | Download Necessary Libraries

To implement ML algorithms, you can either code them from scratch using any programming language like Python, or you can pick one of the following libraries for prompt results. (Once you’ve learned more about ML, you should be able to determine which packages work best for you!)

  1. Scikit-learn
  2. Keras
  3. PyTorch
  4. Tensorflow

You may also need a few additional packages — while writing your ML/DL/CV code — for data handling, numerical calculations, plotting graphs, or image processing tasks. Below are some extensively used libraries in the world of AI:

  1. Pandas for data handling
  2. Numpy for advanced computation
  3. Matplotlib for data visualization
  4. OpenCV for computer vision tasks

Step 3 | Get Started Learning ML, DL, and CV


Here are some of the most encapsulating resources to learn Machine Learning from scratch:

  1. Machine Learning Specialization (Coursera, Andrew Ng): Solid theoretical concepts using either MATLAB or Octave. Free without certification but financial aid is available.
  2. Machine Learning A-Z™: Hands-On Python & R In Data Science: Hands-on learning experiences with Python and R, using Scikitlearn and Keras for implementation of algorithms. Paid.
  3. Machine Learning Engineer (Udacity): Advanced machine learning techniques and algorithms using the PyTorch library. Paid.
  4. Introduction to Machine Learning for Coders (Jeremy Howard, who is Kaggle’s #1 competitor two years running and the founder of Enlitic): In-depth ML concepts. Free.
  5. Machine Learning with Python (Sentex): Video series with a holistic
    understanding of machine learning, covering theory, application, and inner workings of supervised, unsupervised, and deep learning algorithms. Free.
  6. Note: If you find it challenging to learn from the given resources, read this article by Husun Shujaat on learning about AI.
  1. Deep Learning Specialization (Coursera, Andrew Ng): Implementing algorithms in Python, entirely from scratch, without using any library. Free without certification but financial aid is available.
  2. Deep Learning A-Z™: Hands-On Artificial Neural Networks: Designed with Keras and Pytorch. Paid.
  3. Tensorflow in Practice ( Free without a certificate but Financial Aid is available.
  4. Deep Learning Nano Degree: Becoming an expert in neural networks using the PyTorch framework. Paid.
  5. Practical Deep Learning for Coders: Well-documented tutorial covering beginner basics to advanced DL techniques. Free.
  6. Deep Learning Video Series (Sentdex): Introduction to DL using Python, TensorFlow, and Keras. Free. 
  1. Computer Vision Nano Degree: Cutting-edge CV and DL techniques with object tracking and localization concepts, using PyTorch for programming exercises. Paid.
  2. Introduction to CV with Watson and OpenCV (IBM Applied AI Certificate): Covers OpenCV and Watson. Free without certificate but Financial Aid is available.

Are you unable to afford online courses? Fortunately, Coursera has a program of financial assistance for needy learners. Likewise, Udacity provides scholarships to industrious students around the globe.

Step 4 | Follow AI Blogs

Keeping yourself up-to-date with all the latest trends in the universe of AI is an absolute must. Here are some exceptional blogs for you to follow:

  1. Microsoft Machine Learning
  2. Machine Learning Mastery
  3. Towards Data Science

At some point in time, you might feel like giving up your learning journey. It is okay if you are unable to understand something initially. Give it another try, write it down, surf through the internet, ask a mentor, and you will ace it! Perseverance is all that matters.

This Post Has 3 Comments

  1. Samuel C. Nwobodo

    A well detailed brief article

    1. dweebsanddogs

      Thanks, Samuel!

  2. Nkemjika Nwatu

    Thanks Hamza. This is motivating!

Leave a Reply