Build Machine Learning Models Online Course
This course is a complete, hands-on guide to implementing machine learning algorithms from scratch in Python. You’ll learn to load and prepare data, choose evaluation metrics, set up test harnesses, and establish baseline performance. Step-by-step tutorials cover linear, nonlinear, and ensemble algorithms, helping you apply them to real problems without deep mathematical prerequisites. By the end, you’ll understand how popular ML models work behind the scenes and be able to code their core functions for practical, real-world applications.
Who should take this Course?
The Build Machine Learning Models Online Course is ideal for data scientists, machine learning enthusiasts, software developers, and analysts who want to gain practical skills in creating, training, and deploying machine learning models. It’s also suitable for beginners seeking hands-on experience with supervised and unsupervised learning techniques, as well as professionals aiming to integrate ML models into real-world applications. Basic knowledge of Python and data analysis is recommended for optimal learning.
What you will learn
- Develop a baseline expectation of performance for a given problem
- Learn to code the functions of the most used tools in machine learning
- Gain insight into who real-world machine learning models are written
- Gain a deep appreciation for how the algorithm works
- Implement and apply a suite of linear machine learning algorithms
- Implement and apply a suite of advanced non-linear ML algorithms
Course Outline
Introduction
- Introduction
- What is this Course...Exactly?
- Course Outcomes
- Course Structure
- What is an Algorithm in Programming?
Data Preparation
- Loading Data from a CSV File
- Scale Your Data: Normalization
- Scale Your Data: Standardization
- Algorithm Evaluation Methods
- Train-Test Split
- K-Fold Cross-Validation Defined
- K-Fold Cross-Validation
- Choosing a Resampling Method
- Evaluation Metrics
- Classification Accuracy
- Confusion Matrix
- Regression Metrics
- Baseline Models
- Random Prediction Algorithm
- Zero Rule Algorithm
Linear Algorithms
- Algorithm Test Harness - Train-Test-Split
- Algorithm Test Harness - K-Fold
- Simple Linear Regression
- Simple Linear Regression Case Study: Part 1
- Simple Linear Regression Case Study: Part 2
- Multivariate Linear Regression Case Study
- Demo: Multivariate Linear Regression Case Study
- Demo: Linear Regression on Wine Quality Dataset
- Logistic Regression Defined
- Demo: Logistic Regression: Make Predictions
- Demo: Logistic Regression: Estimating Coefficients
- Demo: Logistic Regression: Diabetes Dataset
- Perceptron
- Demo: Perceptron: Make Predictions
- Demo: Perceptron: Training Weights
- Demo: Perceptron: Sonar Dataset
Non-Linear Regression
- Classification and Regression Trees
- Demo: CART: Creating the Gini Index
- Demo: CART: Creating the Splits
- Demo: CART: Evaluating the Splits
- CART: Building the Tree
- Demo: CART: Recursive Splitting
- Demo: CART: Assembling the Tree
- Demo: CART: CART to Banknote Dataset
- Naïve Bayes
- Demo: Naïve Bayes: Separate by Class
- Demo: Naïve Bayes: Summarize the Dataset
- Demo: Naïve Bayes: Summarize Data by Class