The Machine Learning Algorithms A-Z

Curriculum

• Course Introduction Free

  5 Lessons 5 Min

  In this introductory section, you’ll learn which of the course is best for you, the types of ML issues businesses need to solve, and additional resources from the course authors.

  Introduction Free

  ML Algorithms course - GitHub repository Free

  How to Use this Course Free

  Types of ML Problems Free

  Additional Resources Free
• Linear Regression

  17 Lessons 24 Min

  Linear regression is the most dynamic model out of all we review. It’s an exceptional framework for making predictions and extracting insight into relationships between variables.

  Linear Regression Free

  Real World Business Problems Free

  Example: Linear Regression Free

  Intuition: Linear Regression Free

  Training Step-by-Step: Linear Regression Free

  Prediction: Linear Regression Free

  Assumptions: Linear Regression Free

  Assumption #1: Model is linear in coefficients and error terms Free

  Assumption #2: Homoscedasticity Free

  Assumption #3: Multicollinearity Free

  Assumption #4: Independence/Autocorrelation

  Assumption #5: Normally Distributed Error Terms

  Assumption #6: Outliers

  Inference - Interpreting Output

  AB Testing Example

  ML Process: Linear Regression

  Pros & Cons, When to Use
• Ridge, Lasso, Elastic Net

  12 Lessons 14 Min

  One way to limit some of the negatives of linear regression is via regularization. We can regularize a linear regression model using ridge, lasso, and elastic net algorithms.

  Ridge, Lasso, Elastic Net

  Intuition: Ridge, Lasso, Elastic Net

  Plain Definition: Ridge, Lasso, Elastic Net

  Shrinkage Methods vs. Feature Selection

  Step-by-Step Intuition: Ridge, Lasso, Elastic Net

  Lasso Regression (L1)

  Ridge Regression (L2)

  ElasticNet (L1 + L2)

  Determining the Degree of Regularization

  Difference between Lasso & Ridge

  Link to resources

  When to use: Ridge, Lasso, Elastic Net
• Logistic Regression

  14 Lessons 22 Min

  Like linear regression, logistic regression is one of the most powerful and straightforward models.

  Introduction: Logistic Regression

  Example: Logistic Regression

  Intuition: Logistic Regression

  Real World Business Problems: Logistic Regression

  What is Logit

  Step-by-Step Prediction: Logistic Regression

  Step-by-Step Training: Logistic Regression

  Assumptions: Logistic Regression

  Understanding Logistic Regression Output

  Maximum Likelihood Explained

  Log Loss

  Predicting Multiple Classes using Multinomial Logistic Regression

  ML Process: Logistic Regression

  ProsCons, When to Use
• Gradient Descent

  9 Lessons 10 Min

  Gradient descent is an optimization algorithm that powers many of our ML algorithms. Think of it as a helper algorithm, enabling us to find the best formulation of our ML model.

  Gradient Descent

  Intuition: Gradient Descent

  Plain Definition: Gradient Descent

  Step-by-Step: Gradient Descent

  Assumptions: Gradient Descent

  Parameter Tuning (Step size, Alpha)

  Gradient Descent Pros and Cons

  Stochastic Gradient Descent

  Pros and Cons: Gradient Descent
• Decision Trees

  14 Lessons 18 Min

  Decision trees work for classification and regression problems. While individual decision trees don’t typically produce the best predictive outcomes in real life, they are highly interpretable.

  Decision Trees

  Example: Decision Trees

  Plain Explanation: Decision Trees

  Different Components of Decision Trees Explained

  Real World Business Example: Decision Trees

  Assumptions: Decision Trees

  Training Step-by-Step: Decision Trees

  Prediction Step-by-Step: Decision Trees

  Additional Metrics: Decision Trees

  Tuning the Parameters: Decision Trees

  ML Process: Decision Trees

  Assumptions: Decision Trees

  Pros and Cons: Decision Trees

  When to Use Decision Trees.
• Random Forest

  14 Lessons 16 Min

  Random forest is one of the most popular models for classification and regression. It works exceedingly well with datasets with many categorical values or a mix of categorical and continuous variables.

  Random Forest

  Intuition: Random Forest

  Example: Random Forest

  Real World Business Problems: Random Forest

  Plain Definition: Bagging

  Where Bagging Fails

  Plain Definition: Random Forest

  Step-by-Step (Training): Random Forest

  Step-by-Step (Prediction): Random Forest

  How Random Forest give us Feature Importance

  Out of Bag Error

  ML Process: Random Forest

  When to use: Random Forest

  Pros and Cons: Random Forest
• Gradient Boosted Trees

  13 Lessons 17 Min

  Gradient-boosted trees are a way for our models to learn from their mistakes. Unlike random forest—where we grow our trees in parallel, then aggregate the results—with gradient-boosted trees, we grow trees sequentially.

  Gradient Boosted Trees

  Example: Gradient Boosted Trees

  Real World Business Problems: Gradient Boosted Trees

  Plain Definition: Gradient Boosted Trees

  Terminology: Gradient Boosted Trees

  Assumptions: Gradient Boosted Trees

  Training Step-by-Step (Regression): Gradient Boosted Trees

  Training Step-by-Step (Classification): Gradient Boosted Trees

  Prediction Step-by-Step: Gradient Boosted Trees

  What does the “Gradient” mean

  How Gradient Boosted Trees give us Feature Importance

  ML Process: Gradient Boosted Trees

  When to use Gradient Boosted Trees
• XGBoost

  8 Lessons 15 Min

  XGBoost is a famous open-source gradient-boosting algorithm for supervised learning tasks, including regression and classification problems. Reducing errors during each iteration makes better predictions by combining several decision trees.

  Intuition: XGBoost

  Real World Business Problems: XGBoost

  Plain Definition: XGBoost

  XGBoost Algorithm Improvements

  System Improvements

  ML Process: XGBoost

  When to use XGBoost

  Pros and Cons: XGBoost
• K Nearest Neighbors

  9 Lessons 15 Min

  K-nearest neighbors is a popular machine learning algorithm for classifying and predicting data. It works by finding the k closest data points to a new, unknown data point and categorizing it based on the most common class among its neighbors.

  Intuition: KNN

  Example: KNN

  Plain Definition: KNN

  Assumptions : KNN

  Training Step-by-Step: KNN

  Prediction Step-by-Step: KNN

  Tuning Parameters: KNN

  ML Process: KNN

  When to use KNN
• K-Means Clustering

  12 Lessons 16 Min

  K-means clustering is the first unsupervised learning method we will introduce. As a reminder, unsupervised learning means that our data doesn’t have specific target labels we try to classify. Instead, we consider data as a whole and see algorithmically what groups can be made from it.

  Intuition: K-Means Clustering

  Example: K-Means Clustering

  Plain Definition: K-Means Clustering

  Real World Business Problems: K-Means Clustering

  Step-by-Step Training: K-Means Clustering

  Selecting K

  Silhouette Method

  Hard Clustering vs- Soft Clustering

  Derivatives of K-Means

  Assumptions: K-Means Clustering

  ML Process: K-Means Clustering

  When do we use K means Clustering
• Hierarchical Clustering

  9 Lessons 10 Min

  Hierarchical clustering is similar to how you organize files into folders on your computer. Whenever we organize our files into their folders, we perform hierarchical clustering.

  Intuition: Hierarchical Clustering

  Real World Business Problems: Hierarchical Clustering

  Definition: Hierarchical Clustering

  Step-by-Step Agglomerative Clustering

  Linkages

  Distance

  ML Process: Hierarchical Clustering

  Pros and Cons: Hierarchical Clustering

  When to Use: Hierarchical Clustering
• Support Vector Machines

  14 Lessons 18 Min

  Support vector machines (SVMs) work by identifying a hyperplane that best separates the data into different classes or predicts the target variable for regression. It also aims to find the optimal hyperplane that maximizes the margin between the classes while minimizing the misclassification error.

  Intuition: SVM

  Real World Business Problems: SVM

  Step-by-Step Training (Non-Technical): SVM

  Loss Function

  Nonlinear Data

  Prediction (Step-by-Step): SVM

  Terminology: SVM

  Assumptions: SVM

  Soft vs Hard Margins: SVM

  How to use SVMs as a multi-class classifier

  How does SVM Regression Work

  ML Process: SVM

  Pros & Cons (Classifier): SVM

  When to use an SVM Classifier
• Artificial Neural Nets

  13 Lessons 43 Min

  Artificial neural nets (ANNs) are machine learning algorithms based on the structure and function of biological neurons. Layers of interconnected nodes process and transform input data to produce predictions. The neural network learns by adjusting the weights and biases of the connections between the nodes based on the error of the predictions.

  Intuition: Artificial Neural Nets

  Real world Business Problems: Artificial Neural Nets

  Example: Artificial Neural Nets

  Multi-Layered Networks: Artificial Neural Nets

  Classification - Activation Layers

  Vanishing Gradient Problem

  Activation Layers

  Embeddings

  Types of ANNs

  Transfer Learning

  ML Process: Artificial Neural Nets

  Pros and Cons: Artificial Neural Nets

  Conclusion
• Collaborative Filtering - Non-Negative Matrix Factorization

  15 Lessons 18 Min

  Collaborative filtering uses ratings from a group of (collaborative) users to infer the preference of another (filtering) user.

  Intuition: Collaborative Filtering

  Plain Definition: Collaborative Filtering

  Real world Business Problems: Collaborative Filtering

  Assumptions: Collaborative Filtering

  Different Approaches to Collaborative Filtering

  Matrix Factorization Intuition

  Matrix Factorization Definition

  Assumptions: NMF

  Step-by-Step (prediction): Collaborative Filtering

  Step-by-Step (training): Collaborative Filtering

  Determining the ideal number of latent variables

  Addressing the Cold-Start Problem

  ML Process: Collaborative Filtering

  ProsCons: Collaborative Filtering

  When to use NMF
• Naïve Bayes

  10 Lessons 19 Min

  Discover the intricacies of the Naïve Bayes algorithm, exploring Bayes Theorem, its intuitive definition, why it's called "Naïve", the ML process, the pros and cons of this algorithm, a real-life business example, and effective use cases.

  Bayes Theorem

  Intuition and Plain Definition

  Step-By-Strp Explanation - First Part

  Step-by-step Explanation - Second Part

  Why is Naive Baïve called Naïve?

  The types of Naïve Bayes

  ML Process: Naïve Bayes

  Pros and Cons: Naïve Bayes

  Real-Life Business Example

  When to use Naïve Bayes
• Practical projects

  3 Lessons 77 Min

  In this section you can find practical projects that will help you enhance your skills.

  Regression project

  Classification project

  L1 vs L2