Machine Learning Fundamentals

Introduction to the Course

Quickstart

Welcome to the Course

This course is designed to help you learn the necessary skills to develop machine learning systems. It emphasizes deep learning. I have been developing machine learning systems (speech recognition and machine translation systems) for over 25 years and have been helping others learn this material for over 10. I believe this online course to be an effective and fun way to learn these skills. In this course you will learn to build machine learning applications that can solve real world problems. While it may take 10 000 hours of training to become expert in this area you will find that with a small investment of time you can develop skills that you can immediately use to build useful applications.

Intended Audience

This course is intended for people with some experience with Python. In addition some knowledge of the Numpy and Pandas Python libraries will help. If you have strong skills in another programming language you will be fine. If you are a complete beginner this course will be doable but may be challenging.

Modules

On the menu bar at the top of this page you will see that the course consists of a number of modules. These modules are designed to introduce you to the key elements of machine learning and introduce you to the tools you will need to successfully create applications that use machine learning techniques. The only way to proficient with this material is to practice and as such the modules are designed to encourage you in your productive wrangling and applying machine learning techniques to different datasets.

What you’ll learn

In addition to gaining basic fluency with Python Numpy and Pandas you will learn the following.

Core machine learning principles

You will learn how to

  • architect a scalable ML pipeline
  • run ML jobs on a GPU with Jupyter notebooks
  • evaluate different ML models
  • determine the best ML algorithm to use for an application.
  • reduce the dimensionality of a dataset
  • develop different linear models to solve classification problems
  • communicate effectively about ML applications (terminology)

XGBoost

You will learn how to

  • apply decision tree algorithms to create a classifier.
  • use random forest techniques
  • combine a number of weak classifiers into a strong one by using boosting.
  • effectively use the XGBoost algorithm

Deep Learning

You will learn

-how to build a simple deep learning system for image classification.

  • the basic mathematical foundations of deep learning.
  • how to build CNNs for computer vision. -how to build deep learning models to handle text.