Course description

This course is for you if you are new to Machine Learning but want to learn it without all the math. This course is also for you if you have had a machine learning course but could never figure out how to use it to solve your own problems.

In this course, we will start from the very scratch. This is a very applied course, so we will immediately start coding even without installation! You will see a brief bit of absolutely essential theory and then we will get into the environment setup and explain almost all concepts through code. You will be using Keras -- one of the easiest and most powerful machine learning tools out there.

You will start with a basic model of how machines learn and then move on to higher models such as:

  • Convolutional Neural Networks 
  • Residual Connections 
  • Inception Module


All with only a few lines of code. All the examples used in the course comes with starter code which will get you started and remove the grunt effort. The course also includes finished codes for the examples run in the videos so that you can see the end product should you ever get stuck.

There is also a real-time chat system in place for students who enroll in this course. With a free signup, you get access to real-time chat with myself and fellow students who are working to complete this course (or have completed the course before you). We plan on creating this network of like-minded machine learning experts who can help each other out and collaborate on exciting ideas together.


What will I learn? 

  • Basics of machine learning with minimal math
  • A specialized but optional mathematics heavy talk that explains all the inner working of machine learning and deep learning 
  • Applying machine learning principles to solve a real-world case study that includes pre-processing and getting your data into the proper shape. (This case study comes from a real research work I have carried out recently)
  • Understand the often problematic shape issue that makes machine learning difficult to apply in real life 
  • Learn the details of ConvNets and graph-based machine learning models such as Residual Connections and Google's Inception Module 
  • Use Keras's functional API to create powerful models that will help you move way beyond the contents covered in this course 
  • Learn how to use Google's GPUs to speed up your experiments for free
  • Tips on avoiding mistakes made by new-comers to the field and the best practices to get you to your goal with minimal effort 


About the instructor: 

  • Teacher and researcher by profession
  • PhD in Security and a PostDoc from Max Planck Institute for Software Systems, Germany
  • 17+ years of working with computers and 15+ years of teaching experience 
  • 3+ years of working extensively with deep learning. I worked with almost all the modern tools as soon as they were released


Target Audience:

Anyone who:

  • Wants to learn machine learning (this course is a soft introduction)  
  • Knows machine learning and wants to learn deep learning (this course focuses on deep learning
  • Knows deep learning but needs help applying their knowledge in practice (this is a very applied course
  • Comfortable with deep learning models but has trouble processing examples beyond the toy examples covered in typical courses (this course has a real-world case study and not just toy examples) 
  • Is a researchers or educator working in machine learning and wants to move from theory to practice


What you need to know:

  • Python basics (installation, if, loops, lists) - Everything else will be covered in the course
  • No machine learning background is assumed (but we keep the theory to a minimum)

Course curriculum

  • 2
    A Bit of Theory
    • Machine Learning Pipeline
    • Regression
    • Binary and Multi-class Classification
    • Recap and a Link to More Theory
  • 3
    Installation and Setup
    • Environment setup for Windows (and some issues with it)
    • Environment setup for Mac and Linux
  • 4
    Say Hi to Keras
    • Data Preparation
    • Training and Testing
  • 5
    Real World Case Study: Predicting Protein Functions
    • Problem Description and Data View
    • Pre-processing the Data
    • Loading Data and Getting the Shapes Right
    • Train, Test Split
    • Shapes in Depth (or how not to have headaches for days)
    • Sequential Model
    • Functional API
  • 6
    Convolutional Neural Networks (CNN)
    • Basics and Rationale
    • CNN in Keras (or why Keras is better than your ML tool)
    • Pooling (and why it's not that important)
    • Dropout (and why you should always consider it)
  • 7
    Graph-based Models
    • Functional API for CNN
    • Inception Module
    • Residual Connections
  • 8
    Finishing Touches
    • Saving and Loading Model Weights
    • Parting Words
  • 9
    Extra Resources
    • SK learn first file
    • Course Resources Download

Meet your instructor!

Mohammad Nauman
PhD, programmer, researcher, designer and teacher.


I have a PhD in Computer Sciences and a PostDoc from the Max Planck Institute for Software Systems. I have been programming since early 2000 and have worked with many different languages, tools and platforms. 

I have an extensive research experience with many state-of-the-art models to my name. My research in Android security has led to some major shifts in the Android permission model.

I love teaching and the most important reason I upload online is to make sure people can find my content.

Take this course today!

"Practical Deep Learning with Keras and Python"

Bundle including this course!