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. This involves creating datasets that permit generalization; we talk about methods of doing so in a repeatable way so as to support experimentation.
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 1m
- Improve Data Quality: An Introduction 13m
- Lab Intro Improve Data Quality 1m
- Getting Started With GCP And Qwiklabs 4m
- Lab: Improving Data Quality 0m
- Exploratory Data Anlaysis 13m
- Lab Intro Exploratory Data Analysis 1m
- Lab: Exploratory Data Analysis Using Python and BigQuery 0m
- Resources - Readings - Improve Data Quality and Exploratory Data Analysis 0m
- Introduction 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
- Lab Intro: Introduction to Linear Regression 0m
- Lab: Introduction to Linear Regression 0m
- Lab Intro: Introduction to Logistic Regression 0m
- Lab: Introduction to Logistic Regression 0m
- Short history of ML: Decision Trees 6m
- Short History of ML: Random Forests 5m
- Lab Intro: Decision Trees and Random Forests in Python 1m
- Lab: Creating Decision Trees and Random Forests in Python 0m
- Short History of ML: Kernel Methods 5m
- Short History of ML: Modern Neural Networks 9m
- Resources - Readings - Practical ML 0m
- Introduction 1m
- Defining ML Models 4m
- Introducing the Course Dataset 6m
- Introduction Loss Functions 7m
- Gradient Descent 5m
- Troubleshooting Loss Curves 3m
- ML Model Pitfalls 7m
- Lecture Lab: Introducing the TensorFlow Playground 6m
- Lecture Lab: TensorFlow Playground - Advanced 4m
- Lecture Lab: Practicing with Neural Networks 7m
- Lecture Loss Curve Troubleshooting 3m
- Performance Metrics 4m
- Confusion Matrix 6m
- Resources - Readings - Optimization 0m
- Introduction 2m
- Generalization and ML Models 6m
- When to Stop Model Training 5m
- Lecture Creating Repeatable Samples in BigQuery 7m
- Lecture Demo: Splitting Datasets in BigQuery 9m
- Lab Introduction Creating Repeatable Dataset Splits in BigQuery 1m
- Lab: Creating repeatable splits in BigQuery 0m
- Lab Solution Walkthrough Creating Repeatable Dataset Splits in BigQuery 9m
- Lab Introduction Exploring and Creating ML Datasets 2m
- Lab: Exploring and Creating ML Datasets 0m
- Lab Solution Walkthrough Exploring and Creating ML Datasets 23m
- Resources - Readings - Generalization and Sampling 0m
