Build Machine Learning Models Online Course
Build Machine Learning Models Online Course
This comprehensive online course provides a hands-on approach to learning machine learning algorithms by implementing them from scratch in Python. You'll explore data loading, model evaluation, and top machine learning algorithms through step-by-step tutorials. While understanding the math behind algorithms is helpful, this course focuses on practical implementation and real-world results. You’ll learn to prepare data from CSV files, select evaluation metrics, resample techniques, develop baseline models, and apply linear, nonlinear, and ensemble machine learning algorithms to optimize performance. By the end, you’ll be equipped to understand, code, and apply key machine learning models, bridging the gap between theory and practice.
Key Benefits
- Gain a deep understanding of the inner workings of leading machine learning algorithms.
- Learn how to optimally configure machine learning algorithms to maximize their performance.
- Develop an awareness of the numerous fine-grained decisions that are often abstracted away in machine learning libraries, enhancing your practical implementation skills.
Target Audience
This course is designed for developers, machine learning engineers, and data scientists who are eager to optimize their use of Keras. While prior expertise in machine learning is not required, familiarity with solving basic machine learning problems using SciKit-Learn would be beneficial. A strong foundation in Python is also essential to fully engage with the course content.
Learning Objectives
- Establish a baseline performance expectation for various machine learning problems
- Master the coding of functions for the most commonly used tools in machine learning
- Gain a thorough understanding of how real-world machine learning models are constructed and written
- Develop a deep understanding of the inner workings of machine learning algorithms
- Implement and apply a variety of linear machine learning algorithms
- Implement and apply advanced non-linear machine learning algorithms to enhance model performance
Course Outline
The Build Machine Learning Models Exam covers the following topics -
Module 1 - Introduction
- Overview of the Course
- What You Will Learn from This Course
- Expected Outcomes
- Structure of the Course
- Understanding Algorithms in Programming
Module 2 - Data Preparation
- Importing Data from CSV Files
- Data Scaling: Normalization
- Data Scaling: Standardization
- Evaluation Methods for Algorithms
- Train-Test Split Explained
- Defining K-Fold Cross-Validation
- Implementing K-Fold Cross-Validation
- Choosing the Right Resampling Method
- Key Evaluation Metrics:
- Classification Accuracy
- Confusion Matrix
- Regression Metrics
- Baseline Models
- Random Prediction Algorithm
- Zero Rule Algorithm
Module 3 - Linear Algorithms
- Algorithm Test Harness: Train-Test Split
- Algorithm Test Harness: K-Fold
- Introduction to 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 with Wine Quality Dataset
- Understanding Logistic Regression
- Demo: Logistic Regression for Predictions
- Demo: Estimating Coefficients with Logistic Regression
- Demo: Logistic Regression Applied to Diabetes Dataset
- Perceptron Overview
- Demo: Perceptron for Predictions
- Demo: Perceptron for Training Weights
- Demo: Perceptron with Sonar Dataset
Module 4 - Non-Linear Regression
- Classification and Regression Trees (CART)
- Demo: CART and the Gini Index
- Demo: CART: Creating Splits
- Demo: CART: Evaluating Splits
- Building a Decision Tree with CART
- Demo: Recursive Splitting in CART
- Demo: Assembling the CART Tree
- Demo: Applying CART to Banknote Dataset
- Introduction to Naïve Bayes
- Demo: Naïve Bayes: Separation by Class
- Demo: Naïve Bayes: Dataset Summarization
- Demo: Naïve Bayes: Summarizing Data by Class
