Microsoft’s machine learning for beginners

A free, self-paced online course in machine learning is offered by Microsoft’s Azure Cloud Advocates. Its 24-lesson program, which is expected to last 12 weeks, is aimed at beginners in machine learning.

There are many advantages to participating Machine learning for beginners. First, you learn about the currently trending ML concepts, learning skills that are highly sought after by employees. On top of that, you learn them in conjunction with Python, the most popular and versatile language that is also highly sought after.

This role of intermediary between Python and Machine Learning is played by none other than scikit-learn, which is chosen for good reason. As I explained in “Introduction to Machine Learning with Scikit-Learn”.

Python is arguably the most popular language for doing ML, mainly due to the number of relevant libraries available. scikit-learn is one of the best machine learning libraries alongside PyTorch, NumPy, SciPy, TensorFlow, and Theano. Plus, scikit-learn is one of the easiest to learn, perfect for starting your ML journey. This does not mean that it lacks features, however; it is perfectly capable of performing many ML tasks such as classification, clustering, preprocessing, regression, etc.

It’s also important to note that the authors made a clear distinction between machine learning and AI. This course is about “classical machine learning” and is not interested in artificial intelligence, something that its brother course AI for beginners covers. This separation of subjects means that ML for beginners is not as complicated as it would be otherwise.

That being said, let’s focus on the course itself.
As said, although it adapts to its own pace, it spans 12 weeks and 3 months is the expected time to complete it. Being at your own pace rather than instructor-led does not diminish its value. Rather, it is carefully planned and well structured. It includes quizzes, homework, projects, group discussions, and of course, great material.

The course is hosted on GitHub with links to You Tube videos mixed with actual text lessons and includes 24 lessons:

  • Introduction to machine learning
    Learn the basics of machine learning
  • The history of machine learning
  • Fairness and machine learning
    What are the important philosophical questions regarding fairness that students should consider when creating and applying ML models?
  • Pumpkin Prices in North America I
    Visualize and cleanse data for ML
  • Pumpkin Prices in North America II
    Build linear and polynomial regression models
  • Pumpkin Prices in North America III
    Building a logistic regression model
  • A web application
    Create a web application to use your trained model
  • Introduction to ranking
    Clean, prepare and visualize your data; introduction to ranking
  • Delicious Asian and Indian cuisines
    Introduction to Classifiers
  • Delicious Asian and Indian cuisines
    More classifiers
  • Delicious Asian and Indian cuisines
    Create a recommendation web app using your template
  • Introduction to clustering
    Clean, prepare and visualize your data; Introduction to clustering
  • Explore Nigerian Musical Tastes
    Explore the K-Means clustering method
  • Introduction to automatic natural language processing
    Learn the basics of NLP by creating a simple bot
  • Common NLP Tasks
    Deepen your knowledge of NLP by understanding the common tasks required to deal with linguistic structures
  • Translation and sentiment analysis
    Translation and sentiment analysis with Jane Austen
  • Romantic Hotels in Europe
    Sentiment Analysis with 1 Hotel Reviews
  • Romantic Hotels in Europe
    Sentiment Analysis with 2 Hotel Reviews
  • Introduction to time series forecasting
  • Global energy use
    time series forecasting with ARIM
  • Introduction to Reinforcement Learning
    Introduction to Reinforcement Learning with Q-Learning
  • Help Peter avoid the wolf!
    Learning reinforcement
  • Additional lesson: ML scenarios and applications in the real world
    Interesting and revealing real-world applications of classic ML

It is clear from this list that the course teaches many practical applications of ML, mainly focused on its data science side, such as:

  • Predict the likelihood of illness from a patient’s history or medical reports.
  • Use weather data to predict weather events.
  • Understand the feeling of a text.
  • Detect fake news to stop the spread of propaganda.

However, if you are looking for the neural networks side, it is best to go with “AI for Beginners”.

As prerequisites, it is recommended that you have a basic understanding of Python, while a little JavaScript is also required when building the web application project. As for the tools, you will need to have node and npm installed, as well as Visual Studio Code for Python and JavaScript development. And of course a GitHub account. As for Scikit, you are going to use it everywhere, so it is best to familiarize yourself with it.

After going through it, you will be looking for the next steps. The instructors advise you to continue with the next Data science for beginners and, as already mentioned, AI for beginners.

Overall, this course provides a first-class opportunity to start your machine learning journey!

More information

Machine learning for beginners

Related Articles

Introduction to Machine Learning with Scikit-Learn

Learn Python with HackInScience

Fly over the moon with Microsoft and Python

Learn Python with Microsoft or the University of Michigan

To be informed of new articles on I Programmer, subscribe to our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Banner

square

comments

or send your comment to: [email protected]

Leave Comment

Your email address will not be published. Required fields are marked *