Exercises

This page lists the exercises in Machine Learning Crash Course.

The majority of the Programming Exercises use the California housing data set.

Programming exercises run directly in your browser (no setup required!) using the Colaboratory platform. Colaboratory is supported on most major browsers, and is most thoroughly tested on desktop versions of Chrome and Firefox. If you'd prefer to download and run the exercises offline, see these instructions for setting up a local environment.

All

In March, 2020, this course began using Programming Exercises coded with tf.keras. If you'd prefer to use the legacy Estimators Programming Exercises, you can find them on GitHub.

Framing

• Check Your Understanding: Supervised Learning, Features and Labels

Descending into ML

• Check Your Understanding: Mean Squared Error

Reducing Loss

• Optimizing Learning Rate
• Check Your Understanding: Batch Size
• Playground: Learning Rate and Convergence

First Steps with TensorFlow

• Programming Exercise: NumPy Ultraquick Tutorial
• Programming Exercise: pandas UltraQuick Tutorial
• Programming Exericse: Linear Regression with Synthetic Data
• Programming Exercise: Linear Regression with a Real Dataset

Training and Test Sets

• Playground: Training Sets and Test Sets

Validation

• Check Your Intuition: Validation
• Programming Exercise: Validation Sets and Test Sets

Feature Crosses

• Playground: Introducing Feature Crosses, More Complex Feature Crosses
• Check Your Understanding: Feature Crosses
• Programming Exercise: Representation with Feature Crosses

Regularization for Simplicity

• Playground: Overcrossing?
• Check Your Understanding: L₂ Regularization, L₂ Regularization and Correlated Features
• Playground: Examining L₂ Regularization

Classification

• Check Your Understanding: Accuracy, Precision, Recall, Precision and Recall
• Check Your Understanding: ROC and AUC
• Programming Exercise: Binary Classification

Regularization for Sparsity

• Check Your Understanding: L₁ Regularization, L₁ vs. L₂ Regularization
• Playground: Examining L₁ Regularization

Intro to Neural Nets

• Playground: A First Neural Network, Neural Net Initialization, Neural Net Spiral
• Programming Exercise: Intro to Neural Networks

Training Neural Nets

• Backpropagation algorithm visual explanation

Multi-Class Neural Nets

• Programming Exercise: Multi-Class Classification with MNIST

Fairness

• Check Your Understanding: Fairness
• Programming Exericse: Intro to Fairness

Static vs. Dynamic Training

• Check Your Understanding: Online Training, Offline Training

Static vs. Dynamic Inference

• Check Your Understanding: Offline Inference, Online Inference

Data Dependencies

• Check Your Understanding: Data Dependencies

Programming

In March, 2020, this course began using Programming Exercises coded with tf.keras. If you'd prefer to use the legacy Estimators Programming Exercises, you can find them on GitHub.

Framing

• Check Your Understanding: Supervised Learning, Features and Labels

Descending into ML

• Check Your Understanding: Mean Squared Error

Reducing Loss

• Optimizing Learning Rate
• Check Your Understanding: Batch Size
• Playground: Learning Rate and Convergence

First Steps with TensorFlow

• Programming Exercise: NumPy Ultraquick Tutorial
• Programming Exercise: pandas UltraQuick Tutorial
• Programming Exericse: Linear Regression with Synthetic Data
• Programming Exercise: Linear Regression with a Real Dataset

Training and Test Sets

• Playground: Training Sets and Test Sets

Validation

• Check Your Intuition: Validation
• Programming Exercise: Validation Sets and Test Sets

Feature Crosses

• Playground: Introducing Feature Crosses, More Complex Feature Crosses
• Check Your Understanding: Feature Crosses
• Programming Exercise: Representation with Feature Crosses

Regularization for Simplicity

• Playground: Overcrossing?
• Check Your Understanding: L₂ Regularization, L₂ Regularization and Correlated Features
• Playground: Examining L₂ Regularization

Classification

• Check Your Understanding: Accuracy, Precision, Recall, Precision and Recall
• Check Your Understanding: ROC and AUC
• Programming Exercise: Binary Classification

Regularization for Sparsity

• Check Your Understanding: L₁ Regularization, L₁ vs. L₂ Regularization
• Playground: Examining L₁ Regularization

Intro to Neural Nets

• Playground: A First Neural Network, Neural Net Initialization, Neural Net Spiral
• Programming Exercise: Intro to Neural Networks

Training Neural Nets

• Backpropagation algorithm visual explanation

Multi-Class Neural Nets

• Programming Exercise: Multi-Class Classification with MNIST

Fairness

• Check Your Understanding: Fairness
• Programming Exericse: Intro to Fairness

Static vs. Dynamic Training

• Check Your Understanding: Online Training, Offline Training

Static vs. Dynamic Inference

• Check Your Understanding: Offline Inference, Online Inference

Data Dependencies

• Check Your Understanding: Data Dependencies

Check Your Understanding

In March, 2020, this course began using Programming Exercises coded with tf.keras. If you'd prefer to use the legacy Estimators Programming Exercises, you can find them on GitHub.

Framing

• Check Your Understanding: Supervised Learning, Features and Labels

Descending into ML

• Check Your Understanding: Mean Squared Error

Reducing Loss

• Optimizing Learning Rate
• Check Your Understanding: Batch Size
• Playground: Learning Rate and Convergence

First Steps with TensorFlow

• Programming Exercise: NumPy Ultraquick Tutorial
• Programming Exercise: pandas UltraQuick Tutorial
• Programming Exericse: Linear Regression with Synthetic Data
• Programming Exercise: Linear Regression with a Real Dataset

Training and Test Sets

• Playground: Training Sets and Test Sets

Validation

• Check Your Intuition: Validation
• Programming Exercise: Validation Sets and Test Sets

Feature Crosses

• Playground: Introducing Feature Crosses, More Complex Feature Crosses
• Check Your Understanding: Feature Crosses
• Programming Exercise: Representation with Feature Crosses

Regularization for Simplicity

• Playground: Overcrossing?
• Check Your Understanding: L₂ Regularization, L₂ Regularization and Correlated Features
• Playground: Examining L₂ Regularization

Classification

• Check Your Understanding: Accuracy, Precision, Recall, Precision and Recall
• Check Your Understanding: ROC and AUC
• Programming Exercise: Binary Classification

Regularization for Sparsity

• Check Your Understanding: L₁ Regularization, L₁ vs. L₂ Regularization
• Playground: Examining L₁ Regularization

Intro to Neural Nets

• Playground: A First Neural Network, Neural Net Initialization, Neural Net Spiral
• Programming Exercise: Intro to Neural Networks

Training Neural Nets

• Backpropagation algorithm visual explanation

Multi-Class Neural Nets

• Programming Exercise: Multi-Class Classification with MNIST

Fairness

• Check Your Understanding: Fairness
• Programming Exericse: Intro to Fairness

Static vs. Dynamic Training

• Check Your Understanding: Online Training, Offline Training

Static vs. Dynamic Inference

• Check Your Understanding: Offline Inference, Online Inference

Data Dependencies

• Check Your Understanding: Data Dependencies

Playground

In March, 2020, this course began using Programming Exercises coded with tf.keras. If you'd prefer to use the legacy Estimators Programming Exercises, you can find them on GitHub.

Framing

• Check Your Understanding: Supervised Learning, Features and Labels

Descending into ML

• Check Your Understanding: Mean Squared Error

Reducing Loss

• Optimizing Learning Rate
• Check Your Understanding: Batch Size
• Playground: Learning Rate and Convergence

First Steps with TensorFlow

• Programming Exercise: NumPy Ultraquick Tutorial
• Programming Exercise: pandas UltraQuick Tutorial
• Programming Exericse: Linear Regression with Synthetic Data
• Programming Exercise: Linear Regression with a Real Dataset

Training and Test Sets

• Playground: Training Sets and Test Sets

Validation

• Check Your Intuition: Validation
• Programming Exercise: Validation Sets and Test Sets

Feature Crosses

• Playground: Introducing Feature Crosses, More Complex Feature Crosses
• Check Your Understanding: Feature Crosses
• Programming Exercise: Representation with Feature Crosses

Regularization for Simplicity

• Playground: Overcrossing?
• Check Your Understanding: L₂ Regularization, L₂ Regularization and Correlated Features
• Playground: Examining L₂ Regularization

Classification

• Check Your Understanding: Accuracy, Precision, Recall, Precision and Recall
• Check Your Understanding: ROC and AUC
• Programming Exercise: Binary Classification

Regularization for Sparsity

• Check Your Understanding: L₁ Regularization, L₁ vs. L₂ Regularization
• Playground: Examining L₁ Regularization

Intro to Neural Nets

• Playground: A First Neural Network, Neural Net Initialization, Neural Net Spiral
• Programming Exercise: Intro to Neural Networks

Training Neural Nets

• Backpropagation algorithm visual explanation

Multi-Class Neural Nets

• Programming Exercise: Multi-Class Classification with MNIST

Fairness

• Check Your Understanding: Fairness
• Programming Exericse: Intro to Fairness

Static vs. Dynamic Training

• Check Your Understanding: Online Training, Offline Training

Static vs. Dynamic Inference

• Check Your Understanding: Offline Inference, Online Inference

Data Dependencies

• Check Your Understanding: Data Dependencies