Course
Skills
Launching into Machine Learning
Starting from a history of machine learning, we discuss why neural networks today perform so well in a variety of problems. We then discuss how to set up a supervised learning problem and find a good solution using gradient descent.
What you'll learn
Starting from a history of machine learning, we discuss why neural networks today perform so well in a variety of problems. We then discuss how to set up a supervised learning problem and find a good solution using gradient descent. This involves creating datasets that permit generalization; we talk about methods of doing so in a repeatable way so as to support experimentation.
Table of contents
Introduction
8mins
Practical ML
64mins
- Introduction to Practical ML 1m
- Supervised Learning 6m
- Regression and Classification 11m
- Short history of ML: Linear Regression 8m
- Short history of ML: Perceptron 5m
- Short history of ML: Neural Networks 8m
- Short history of ML: Decision Trees 6m
- Short history of ML: Kernel Methods 5m
- Short history of ML: Random Forests 5m
- Short history of ML: Modern Neural Networks 9m
Optimization
61mins
- Introduction to Optimization 1m
- Defining ML Models 4m
- Introducing the Course Dataset 6m
- Introducing Loss Functions 7m
- Gradient Descent 5m
- Troubleshooting a Loss Curve 3m
- ML Model Pitfalls 6m
- Activity: Introducing the TensorFlow Playground 6m
- Activity: TensorFlow Playground - Advanced 4m
- Activity: Practicing with Neural Networks 7m
- Activity: Loss Curve Troubleshooting 2m
- Performance Metrics 4m
- Confusion Matrix 6m
Generalization and Sampling
64mins
- Introduction to Generalization and Sampling 2m
- Generalization and ML Models 6m
- When to Stop Model Training 5m
- Creating Repeatable Samples in BigQuery 7m
- Demo: Creating Repeatable Samples in BigQuery 9m
- Lab Intro: Creating Repeatable Dataset Splits 1m
- Lab: [ML on GCP C2] Creating repeatable splits in BigQuery 0m
- Lab Solution - Creating Repeatable Dataset Splits 9m
- Lab Intro: Exploring and Creating ML Datasets 2m
- Lab: [ML on GCP C2] Exploring and Creating ML Datasets 0m
- Lab Solution - Exploring and Creating ML Datasets 23m
Summary
3mins
