Beginner13 min read
What Is Machine Learning?
A plain-language introduction to machine learning: what it is, why it exists and how it differs from the step-by-step programming you may already know.
ML Fundamentals
Machine learning, taught from first principles
Learn machine learning visually, simply, in Python.
Every idea starts with plain language and a picture before it ever reaches a formula or a line of code, so the concepts stick, not just the syntax.
Linear regression
Start here
A short path through the essentials, from what machine learning is to your first neural network.
- Beginner12 min read
Supervised Learning
Supervised learning is the branch of machine learning where the model learns from examples whose correct answer is already known, using features to predict a label.
Supervised Learning
- Beginner16 min read
Linear Regression
Linear regression predicts a number by fitting the straight line that best matches your data. Includes an interactive best-fit line you can drag and reshape yourself.
Supervised Learning
- Beginner15 min read
Classification: Predicting a Category
Classification is the supervised learning task of predicting a category. This lesson covers binary vs. multiclass problems and how to judge a classifier with a confusion matrix.
Supervised Learning
- Beginner14 min read
K-Means Clustering
K-Means groups unlabeled data into K clusters by repeatedly assigning points to the nearest center and moving that center to their average.
Unsupervised Learning
- Advanced18 min read
Neural Networks
Neural networks build predictions from simple neurons stacked in layers. This lesson covers a single neuron, forward propagation and how backpropagation trains one.
Neural Networks
The full curriculum
Every path and every lesson, in order. Available lessons link straight through; the rest show where the map is still being drawn.
- 1What Is Machine Learning?
- 2AI vs. Machine Learning vs. Deep Learning
- 3Types of Machine Learning: Supervised, Unsupervised and Reinforcement
- 4How Machines Learn From Data: Features, Labels and Models
- 5The Machine Learning Workflow: From Data to Deployment
- 6Training, Validation and Test Sets
- 7Overfitting and Underfitting
- 8Evaluating Model Performance
- 1Understanding Your Dataset: Rows, Columns and Data Types
- 2Handling Missing Data
- 3Encoding Categorical Data: One-Hot and Label Encoding
- 4Feature Scaling: Normalization and Standardization
- 5Feature Engineering: Creating Better Inputs
- 6Detecting and Handling Outliers
- 7Train/Test Split and Cross-Validation in Practice
- 8Working with Imbalanced Datasets
Supervised Learning12/12
- 1Supervised Learning
- 2Regression: Predicting a Number
- 3Linear Regression
- 4Regularization: Ridge, Lasso and Preventing Overfitting
- 5Classification: Predicting a Category
- 6Logistic Regression
- 7Naive Bayes Classifiers
- 8K-Nearest Neighbors (KNN)
- 9Decision Trees
- 10Random Forests
- 11Gradient Boosting: XGBoost and Friends
- 12Support Vector Machines (SVM)
- 1Neural Networks
- 2Activation Functions: ReLU, Sigmoid and Tanh
- 3Training a Neural Network: Loss, Optimizers and Learning Rate
- 4Convolutional Neural Networks for Images
- 5Recurrent Neural Networks for Sequences
- 6Transfer Learning: Reusing What a Model Already Knows
- 7An Introduction to TensorFlow and PyTorch
ML Projects7/7