Build Machine Learning Systems from Scratch
Aki Wijesundara, PhD
AI Founder | Google AI Accelerator Alum
Manu Jayawardana
Exited AI Founder | Co-Founder, Snapdrum
Go from no machine learning background to building real models.
Many aspiring learners get stuck at the start. They know what machine learning can do but struggle to turn raw data into models that actually work. Without strong fundamentals, models break, results are unreliable, and it becomes hard to know what is really happening under the hood.
This course guides you from zero to practical machine learning thinking. Over the course, you will learn to:
Understand core machine learning concepts from the ground up
Prepare, clean, and organize data for modeling
Build and train machine learning models step by step
Evaluate, debug, and improve model performance
By the end, you will not just understand the theory. You will build working machine learning models, understand how data becomes predictions, and gain the confidence to apply machine learning to real problems, creating a strong foundation for advanced AI and data work.
What you’ll learn
Build machine learning models from scratch, even if you have never worked with machine learning before.
What machine learning is and how it works
The difference between supervised and unsupervised learning
How data flows through a machine learning system
Collecting and understanding datasets
Cleaning and preparing data for modeling
Turning raw data into useful features
Training simple machine learning models
Understanding how models learn from data
Making predictions and interpreting results
Measuring model performance with basic metrics
Identifying common modeling mistakes
Improving results through iteration and experimentation
Who this course is for
Beginners who want to learn machine learning from scratch
Career switchers looking to enter machine learning or AI roles or Developers who want a strong foundation in machine learning
Students exploring a future in AI, data, or software engineering or anyone curious about machine learning and wants to build real models
Course syllabus
8 live sessions • 140 lessons
Week 1
Feb
3
Foundations of Machine Learning
What machine learning is and when to use it
Types of machine learning: supervised and unsupervised
How data flows through a machine learning system
Understanding features, labels, and datasets
Common machine learning use cases in the real world
Common beginner mistakes and misconceptions
Hands-On Outcome
Resources
Useful Interviews
Articles
Feb
6
Office Hours
Week 2
Feb
10
Working with Data
Understanding raw vs cleaned data
Handling missing and inconsistent values
Basic data transformation and normalization
Feature selection and feature creation
Splitting data into training and testing sets
Avoiding data leakage
Hands-On / Outcome
Articles
Feb
13
Office Hours
Schedule
Live sessions
2 hrs / week
Tue, Feb 3
6:00 PM—8:00 PM (UTC)
Fri, Feb 6
7:30 PM—8:30 PM (UTC)
Tue, Feb 10
3:30 PM—5:30 PM (UTC)
Hands On Projects
4 hrs / week
Complete practical exercises and mini-projects that simulate real-world machine learning workflows. Apply what you learn in live sessions to prepare data, train models, evaluate performance, and iterate on improvements, ensuring you gain hands-on experience that prepares you to build and use machine learning models confidently in real-world setting
Office Hours
1 hr / week
$999
USD
2 days left to enroll