Gain insights into ML fundamentals, foundational mathematics, coding models, and real-world apps. Discover making perceptrons and exploring scikit-learn for classification, regression, and clustering.

ml101.tar.gz

python_cw

python_ml_galaxies

python_ml_3galaxies

This course explains machine learning for absolute beginners by building a visual understanding of the underlying concepts. It covers some foundational mathematics behind the machine learning models and then guides you in coding for models to solve real-world machine learning problems.

You’ll begin by understanding the limitations of traditional coding techniques in solving machine learning problems. Next, you’ll get familiar with the machine learning process. Then, you’ll build your first machine learning model from scratch—a single perceptron. The course then takes you from a single neuron to a multilayer perceptron to solve a non-linearly separable classification dataset. Finally, the course introduces Python’s library, scikit-learn, where you’ll learn to build models for classification, regression, and unsupervised clustering. 

This course aims to make you a lifelong learner and serves as a great starting point for a successful career in machine learning.

Machine Learning for Beginners

Learn how to extend the output classes beyond binary classification and identify what needs to be changed to solve a multiclass problem.

The Machine Learning Problem

The Machine Learning Process

From a Single Neuron to Artificial Neural Networks

Code for Machine Learning Using scikit-learn

Concluding Thoughts

How to Predict the Traffic Volume Using Machine Learning

Recognizing More Objects—Multiclass Classification

Beyond two classes

Multiple output layer neurons